摘要
几千年来,如何确保信息在通信过程中的安全一直是人类面临的重要研究课题。随着网络及多媒体技术的飞速发展,以“隐匿秘密通信存在”为目的的信息隐藏重新受到了人们的广泛关注。在这种通信范式下“隐藏信息”和“检测信息”的隐密对抗问题也迅速成为学术界的研究热点。本文针对目前隐密对抗领域仍存在的诸多关键问题,分别从隐密安全性、隐密方法和隐密分析方法三个方面对隐密对抗所涉及的理论及方法进行了系统研究,主要工作和成果总结如下:
在隐密安全性的理论方面,首先分析了现有隐密安全性理论模型的局限性,阐明了区分“含密数据安全性”和“隐密算法(或系统)安全性”的重要意义,并在全信息视角下重新探讨了隐密安全性的内涵,指出隐密本质上源于认识主体对客观事物全信息的有限认识能力。在此基础上引入“载体分布边界”的概念,构建了新的统计安全性理论框架,明确给出了含密数据安全性、隐密算法安全性和载体数据安全隐密容量的定义,并建立了隐密算法“未公开”和“已公开”两种情况下的隐密安全性描述及度量模型。
在隐密模型及方法的设计方面,首先分析了典型隐密技术的基本原理,并将隐密技术区分为约束式隐密技术和启发式隐密技术。其中,“约束式”是指以明确的隐密安全性理论为指导的隐密技术设计思想;“启发式”是指源于对隐密安全性经验性认识的设计思想。在此基础上,研究了统计安全性约束下的隐密模型,探讨了几个启发式隐密的关键问题,并分别采用直方图预膨胀策略和粒子群优化策略,提出了基于预处理的启发式隐密方法和基于统计安全性约束的隐密方法。
在隐密分析模型及方法的设计方面,首先分析了现有隐密分析技术的设计思想,从方法论的视角将其分类为“概率演绎”隐密分析和“统计归纳”隐密分析(简称统计隐密分析)。进而在统计隐密分析范畴下给出了定性与定量隐密分析问题的数学描述,并应用有限样本集下的统计学习理论提出了相应的定性与定量隐密分析方法,包括基于载体分布边界的隐密判决方法、基于多类分类的数据来源判别方法、基于多元线性回归的隐密分析方法和基于支持向量回归的隐密分析方法。同时从统计特征整体性、集成学习方法和训练样本规模三个角度研究了进一步提高隐密分析性能的途径。
For thousands of years, it has always been a significant research problem to seek secure ways for communicating sensitive information. With the rapid development of networks and multimedia technology, the ancient information hiding method has been rediscovered and received considerable attention, for concealing the very presence of secret communication in digital world is much easier. Consequently, the "hide and seek" problem under this secure communication paradigm, which is also called the "countermeasure between steganography and steganalysis", is becoming a hot topic for academic research in recent years. Aiming at the various problems in this field, a systematic study on steganographic countermeature has been made on the aspects of "security theory", "steganographic method" and "steganalytic method" respectively. The main contribution of this dissertation is as follows:
As to the study of security theory, an analysis on the limitation of current theories and models on steganographic security is presented firstly, and then the difference between "stego data security" and "steganographic system (algorithm) securiy" is clearified. Under the perspective of comprehensive information theory, the connotation of steganographic security is rediscussed and a conclusion is drawn that steganography originates from the limited cognitive ability of subject to object in the sense of comprehensive information. Furthermore, a novel framework of steganographic security is constructed based on the concept of "cover distribution boundary", and some essential concepts are explicitly defined, including stego data security, steganographic system securiy and secure steganographic capacity of cover data. Finally, according to whether the steganographic algorithm is released or not, two security measurement models under this framework are presented, respectively.
As to the steganographic model and method, the design principles of current typical steganographic technologies are analyzed at first. Moreover, heuristic steganography and constrained steganography are differentiated on the basis of different design ideas, with the former constrained by security measurement models and the latter originated from experiential understanding of security. In addition, a steganographic model constrained by statistical security is put forward and some key questions about heuristic steganography are discussed. Finally, a novel heuristic steganographic method and a novel constrained steganographic method are proposed, utilizing histogram preprocessing strategy and binary particle swarm optimization strategy respectively.
As to the steganalytic model and method, different design ideas are summarized from the methodological point of view, and steganalytic technologies are reclassified as probabilistic deduction steganalysis and statistical induction steganalysis (statistical steganalysis for short). Furthermore, mathematical description of qualitative steganalysis and quantitative steganalysis are presented respectively under the category of statistical steganalysis. On the basis of these work, a series of novel steganalytic methods are proposed applying statistical learning theory in finite sample space, including steganalytic discriminant method based on cover distribution boundary, source forensic method based on multi-classification, quantitative steganalytic method based on multivariate regression and quantitative steganalytic method based on support vector regression. Finally, three approaches are studied to further improve steganalytic performance from the angles of holistic statistical features, ensemble learning and the scale of training database.
引文
[1]何德全.维护国家信息安全刻不容缓[J/OL].中国计算机报,1999,82:[1999-11-04].http://media.ccidnet.com/media/ciw/872/b1201.htm.
[2]WANG H,WANG S.Cyber warfare:steganography vs.steganalysis[J].Communication of ACM,2004,47(10):76-82.
[3]KAHN D.The codebreakers-the story of secret writing[M].New York:Scribner,1996:523-525.
[4]PETITCOLAS F A P,ANDERSON R J,KUHN M G.Information hiding-a survey[J].Proceedings of the IEEE special issue on protection of multimedia content.1999,87(7):1062-1078.
[5]NEWMAN B.Secrets of german espionage[M].London:Robert Hale Ltd,1940.
[6]尤新刚,周琳娜,郭云彪.信息隐藏学科的主要分支及术语.全国第三届信息隐藏学术研讨会(CIHW2001)[C].西安,2001:43-50.
[7]COX I J,MILLER M L.The first 50 years of electronic watermarking[J].EURASIP Journal on Applied Signal Processing,2002,2:126-132.
[8]LAMPSON B W.A note on the confinement problem[J].Communications of the ACM,1973,16(10):613-615.
[9]CHAUM D L.Untraceable electronic mail,return addresses and digital pseudonyms[J].Communications of the ACM,1981,24(2):84-90.
[10]KATAOKA T,TANAKA K,NAKAMURA Y,et al.Embedding a document into color picture data under adaptive discrete cosine transform coding[J].Trans.IEICE,1989:1210-1216.
[11]TANAKA K,NAKAMURA Y,MATSUI K.Embedding secret information into dithered multilevel images.Military Communications Conference[C].Monterey,CA,USA,1990(1):216-220.
[12]CHANDRAMOULI R,KHARRAZI M,AND MIEMON N.Image steganography and steganalysis:concepts and practices.Proc.2nd Int.Workshop Digital Watermarking[C].Seoul,Korea,2003:35-49.
[13]FRIDRICH J.AND GOLJAN M.Practical steganalysis of digital images state of the art [J].Electronc Imaging Science Technology,2002,4675:1-13.
[14]SIMMONS G J.The prisoners' problem and the subliminal channel[J].Proceedings of CRYPTO'83.Plenum Press,1984:51-67.
[15]LOW S H,MAXEMCHUK N F,BRASSIL J T,et al.Document marking and identification using both line and word shifting.Proceedings of the Fourteenth Annual Joint Conference of the IEEE Computer and Communication Societies[C],Boston,USA,1995,2:853-860.
[16]GRUHL D,LU A,BENDER W.Echo hiding[J].First International Workshop.Cambridge,U.K.Lecture Notes in Computer Science,1996,1174:293-315.
[17]PETITCOLAS,F.A.P.MP3Stego[EB/OL].2002. http://www. cl. cam. ac.uk/~fapp2/steganography/mp3stego/.
[18] Steg Shell [EB/OL]. http://www.tiac.net/users/korejwa/jstegshella.zip
[19] JP Hide&Seek [EB/OL]. http://linux01.gwdg.de/-alatham/stego.html
[20] Digital Picture Envelope [EB/OL]. ftp://pckawa01. know. comp. kyutech. ac. jp/pdf-filesdown/8EJ-pdf. pdf
[21] WbStego [EB/OL]. http://www. filetransit. com/files. php?name=Wbstego
[22] Invisible Secrets [EB/OL]. http://www.invisiblesecrets.com/
[23] S-Tools [EB/OL]. http://www.spychecker.com/program/stools.html
[24] Stash-It [EB/OL]. http://www.smalleranimals.com/stash.htm
[25] Encrypt Pic [EB/OL]. http://www.winsite.com/bin/Info?500000033023
[26] Gifshuffle [EB/OL]. http://www.darkside.com.au/gifshuffle/
[27] Gif-It-Up [EB/OL]. http://www.theargon.com/achilles/steganography/gif-it-up/
[28] Hide In Picture [EB/OL]. http://sourceforge.net/projects/hide-in-picture/
[29] Steghide [EB/OL]. http://steghide.sourceforge.net/
[30] Stealthencrypt [EB/OL]. http://www.jjtc.com/Steganography/tools.html
[31] Steganos Security Suite [EB/OL]. http://www.steganos.com/
[32] LEE Y K, CHEN L H. An adaptive image steganographic model based on minimum-error LSB replacement. Ninth National Conference on Information Security [C]. Taichung, Taiwan, 1999:8-15.
[33] LISA M M, CHARLES T R, CHARLES G B, et al. Hidding information in images. International Conference on Image Processing, 1998, 2:396-398.
[34] KAWAGUCHI E, O. EASON R. Principle and applications of BPCS-steganography [J]. SPIE's International Symposium on Voice, Video, and Data Communications. 1998, 3528:464-473.
[35] HIROHISA H. A data embedding method using BPCS principle with new complexity measures. Proc. Pacific Rim Workshop on Digital Steganography 2002 (STEG'02) [C]. 2002:30-47.
[36] FRIDRICH J, GOLJAN M. Digital image steganography using stochastic modulation. Proceedings of SPIE: Security and Watermarking of Multimedia Contents V [C]. Santa Clara CA, 2003(5020):191-202.
[37] CHAN C K, CHENG L M. Hiding data in images by simple LSB substitution [J]. Pattern Recognition, 2004, 37:469-474.
[38] FRIDRICH J, DU R, GOLJAN M. Detecting LSB steganography in color and greyscale images [J]. Magazine of IEEE Multimedia Special Issue on Security, 2001, 10:22-28.
[39] WU D C, TSAI W H. A steganographic method for images by pixel-value differencing [J]. Pattern Recognition Letters, 2003, 24(9):1613-1626.
[40] ALTURKI F, MERSEREAU R. A novel approach for increasing security and data embedding capacity in images for data hiding applications. International Conference on Information Technology: Coding and Computing [C]. Las Vegas, 2001:228-233.
[41] ALTURKI F, MERSEREAU R. Secure blind image steganographic technique using discrete Fourier transformation. International Conference on Image Processing [C]. Thessaloniki, Greece, 2001, 2:542-545.
[42] OGIHARA T, NAKAMURA D, YOKOYA N. Data embedding into pictorial images with less distortion using discrete cosine transform. Proceedings of International Conference on Pattern recognition [C]. Vienna, 1996:675-679.
[43] ROMANA MACHADO. Ezstego [EB/OL]. http://www.securityfocus.com/tools/586
[44] FRIDRICH J. A new steganographic method for palette-based images. Proceedings of the IS&T PICS conference [C]. Savannah, Georgia, 1998:285-289.
[45] WU M, HO Y, LEE J. An iterative method of palette-based image steganography [J]. Pattern Recognition Letters, 2004, 25:301-309.
[46] BRISBANE G, SAFAVI-NAINI R, OQUNBONA P. High-capacity steganography using a shared colour palette. IEE Proceedings on Vision, Image and Signal Processing [C]. 2005, 152(6): 787-792.
[47] JPEG-JSteg-V4 [EB/OL]. http://zooid. org/~paul/crypto/jsteg/
[48] LATHAM A. JPHIDE and JPSEEK [EB/OL]. 1999. http://linux01. gwdg. de/-alatham/stego. html
[49] WESTFELD A. F5-a steganographic algorithm: high capacity despite better steganalysis. Information Hiding 4th International Workshop [C]. Pittsburgh, USA, 2001: 289-302.
[50] PROVOS N. Defending against statistical steganalysis. Proc. 10th Usenix Security Symposium [C]. Washington, USA, 2001:323-335.
[51] ZHANG X P, WANG S Z. Secure steganographic embedding in JPEG images against blockness analysis [J]. Journal of Image and Graphics, 2003, 8(A):558-562.
[52] SOLANKI K, SULLIVAN K, MADHOW U, et al. Provably secure steganography: achieving zero K-L divergence using statistical restoration. IEEE International Conference on Image Processing [C]. Atlanta, Georgia, USA, 2006:125-128.
[53] SARKAR A, SOLANKI K, MADHOW U, et al. Secure steganography: statistical restoration of the second order dependencies for improved security. IEEE International Conference on Acoustics, Speech, and Signal Processing [C]. Honolulu, Hawaii, 2007:277-280.
[54] SALLEE P. Model-based steganography. International Workingshop on Digital Watermarking (IWDW2003) [C]. Seoul, Korea, 2003:254-260.
[55] SALLEE P. Model-based methods for steganography and steganalysis [J]. International Journal of Image and Graphics, 2005, 5(1):167-190.
[56] FRIDRICH J, GOLJAN M, SOUKAL D. Perturbed quantization steganography with wet paper codes. Proceedings of the 2004 workshop on Multimedia and security [C]. Magdeburg, Germany, 2004:4-15.
[57] FRIDRICH J, PEVNY T, KODOVSKY J. Statistically undetectable jpeg steganography: dead ends challenges, and opportunities. Proceedings of the 9th workshop on Multimedia & security [C]. Dallas, Texas, USA, 2007:3-14.
[58] KIM Y, DURIC Z, RICHARDS D. Modified matrix encoding technique for minimal distortion steganography [J]. Lecture Notes in Computer Science, 2007, 4437:314-327.
[59] NEWMAN RE, MOSKOWITZ I S, CHANG L W, et al. A steganographic embedding undetectable by JPEG-compatibility steganalysis [J]. Information Hiding, 5th International Workshop, Lecture Notes in Computer Science, 2002, 2578:258-277.
[60] SOLANKI K, SARKAR A, MANJUNATH B S. YASS: yet another steganographic scheme that resists blind steganalysis [J]. Lecture Notes in Computer Science, 2008, 4567:16-31.
[61] JOHNSON N F, JAJODIA S. Steganalysis: the investigation of hidden information. IEEE Conference on Information technology [C]. Syracuse,New York,USA, 1998:113- 116.
[62] NEIL F J, SUSHIL J. Steganalysis of images created using current steganography software. Proceeding of the Second International Workshop on Information Hiding [C]. Portland, Oregon, USA, 1998: 273-289.
[63] WESTFELD A, PFITZMANN A. Attacks on steganographic systems [J]. 3rd International Workshop. Lecture Notes in Computer Science, 2000, 1768:61-75.
[64] WESTFELD A. Detecting low embedding rates [J]. Information Hiding: 5th International Workshop. Lecture Notes in Computer Science, 2002, 2578:324-339.
[65] AVCIBAS I, MEMON N, SANKAR B. Steganalysis based on image quality metrics. Proc of the IEEE 4th Workshop on Multimedia Signal Processing [C]. Canners, France, 2001:517-522.
[66] AVCIBAS I, SANKUR B, MEMON N. Image steganalysis with binary similarity measures. Proceedings of International Conference on Image Processing [C]. Rochester, New York, USA, 2002: 645-648.
[67] AVCIBAS I, KHARRAZI M, MEMON N, et al. Image steganalysis with binary similarity measures [J]. EURASIP Journal on Applied Signal Processing. 2005, 17:2749-2757.
[68] LYU S, FARID H. Detecting hidden messages using higher-order statistics and support vector machines. 5th International Workshop on Information Hiding [C]. Noordwijkerhout, the Netherlands, 2002:340-354.
[69] LYU S, FARID H. Steganalysis using colour wavelet statistics and one-class vector support machines. SPIE Symposium on Electronic Imaging [C]. San Jose, CA, 2004: 35-45.
[70] LYU S, FARID H. Steganalysis using higher-order image statistics [J]. IEEE Transactions on Information Forensics and Security, 2006, 1(1):111-119.
[71] HARMSEN J J. Steganalysis of additive noise modelable information hiding. Proc. On Security and Watermarking of Multimedia Contents V [C]. SPIE 2003, 5020:131-142.
[72] XUAN G R, SHI Y Q, GAO J J, et al. Steganalysis based on multiple features formed by statistical moments of wavelet characteristic functions [J]. Information Hiding 05, LNCS 2005, 3727:262-277.
[73] FRIDRICH J, GOLJAN M, DU R. Steganalysis based on JPEG compatibility. Proc. SPIE Multimedia Systems and Applications IV [C]. Vol. 4518. Denver, Colorado, 2001:281-291.
[74] FRIDRICH J, GOLJAN M, HOGEA D. Steganalysis of JPEG images: breaking the F5 algorithm. Proceeding of 5th Information Hiding Workshop [C]. Noordwijkerhout, Netherlands, 2002:310-323.
[75] FRIDRICH J, GOLJAN M, HOGEA D. Attacking the OutGuess. Proceedings of the. ACM Workshop on Multimedia and Security [C]. Juan-les-Pins, France, 2002:3-6.
[76] FRIDRICH J. Feature-based steganalysis for JPEG images and its implication for future design of steganographic schemes [J]. IH 2004, LNCS 3200. Springer-Verlag Berlin Heidelberg, 2004: 67-81.
[77] PEVNY T, FRIDRICH J. Determining the stego algorithm for JPEG images [J]. IEEE Proc. Information Security, 2006, 153(3):77-86.
[78] FRIDRICH J, GOLJAN M, DU R. Reliable detection of LSB steganography in color and grayscale images. Proc, of the ACM Workshop on Multimedia and Security [C]. New York, NY, USA, 2001:27-30.
[79] KER A. Steganalysis of LSB matching in grayscale images [J]. IEEE Signal Processing Letters, 2005, 12(6):441-444.
[80] KER A. Resampling and the detection of LSB matching in color bitmaps. Proceedings of Security, Steganography, and Watermarking of Multimedia Contents VII [C]. San Jose, California, USA, 2005:1-15.
[81] FRIDRICH J, SOUKAL D, GOLJAN M. Maximum likelihood estimation of length of secret message embedded using ±K steganography in spatial domain. Security, Steganography, and Watermarking of Multimedia Contents VII [C]. San Jose, California, USA. Proceedings of SPIE 5681 SPIE, 2005: 595-606.
[82] HOLOTYAK T, FRIDRICH J, SOUKAL D. Stochastic approach to secret message length estimation in ±K steganography. Proceedings of Security, Steganography, and Watermarking of Multimedia Contents VII [C]. San Jose, California, USA, 2005:673-684.
[83] ZHANG T, PING X J. A fast and effective steganalytic technique against Jsteg-like algorithms. Proceedings of ACM Symposium on Applied Computing [C]. Florida, USA, 2003: 307-311.
[84] FRIDRICH J, GOLJAN M, HOGEA D. Quantitative Steganalysis: estimating secret message length [J]. ACM Multimedia Systems Journal, Special issue on Multimedia Security, 2003, 9(3):288-302.
[85]FRIDRICH J.Forensic steganalysis:determining the stego key in spatial domain steganography.Proc.SPIE,Electronic Imaging,Security,Steganography,and Watermarking of Multimedia Contents Ⅶ[C].San Jose,2005:631-642.
[86]FRIDRICH J,GOLJAN M,SOUKAL D.Searching for the stego-key.Security,stenography,and watermarking of multimedia contents Ⅵ[C].San Jose CA,2004,5306:78-82.
[87]KESSLER G C.An overview of steganography for the computer forensics examiner[J].Forensic Science Communications,2004,6(3):45-48.
[88]郭艳卿,何德全,尤新刚,等.基于整体性的隐密分析特征提取和融合方法研究[J].电子学报,2006,34(12A):2443-2446.
[89]Z(O|¨)LLNER J,FEDERRATH H,KLIMANT H,et al.Modeling the security of steganographic systems[J].Proceedings of the Second International Workshop on Information Hiding.Lecture Notes in Computer Science,1998,1525:344-354.
[90]CACHIN C.An information-theoretic model for steganography.Information Hiding:Second International Workshop[C].Portland,Oregeon,U.S.A.,1998:306-318.
[91]CHANDRAMOULI R,LI G,MEMON N.Adative steganography.Security and watermarking of multimedia contents Ⅳ[C].San Jose CA,2002,4675:69-78.
[92]WANG Y,MOULIN P.Steganalysis of block-structured stegotext.Security,stenography,and watermarking of multimedia contents Ⅵ[C].San Jose CA,2004,5306:477-488.
[93]陈丹,王育民.基于图像模型的掩密安全性定义[J].哈尔滨工业大学学报,2006,38(S):901-904.
[94]COX I J,KALKER T,PAKURA G,et al.Information transmission and steganography.International Workshop of Digital Watermarking[J].Lecture Notes in Computer Science,2005,3710:15-29.
[95]KATZENBEISSER S,PETITCOLAS F A P.On defining security in steganographic systems.Security and watermarking of multimedia contents Ⅳ[C].San Jose CA,2002,4675:50-56.
[96]HOPPER N J,LANGFORD J,AHN L V.Provably secure steganography[J].Lecture Notes in Computer Science.2002,2442:119-123.
[97]KIAYIAS A,RAEKOW Y,RUSSELL A.Efficient steganography with provable security guarantees.7th International Workshop,IH 2005[C].Barcelona,Spain,Lecture Notes in Computer Science.2005,3727:118-130.
[98]MOSKOWITZ I S,LONGDON G E,CHANG L W.A new paradigm hidden in steganography.Proceedings of the 2000 workshop on new security paradigms[C].Ballycotton,County Cork,Ireland,2001:41-50.
[99]CHANDRAOULI R,MEMON N D.Steganography capacity:a steganalysis perspective.Security and watermarking of multimedia contents Ⅴ[C].Santa Clara CA,2003,5020:173-177.
[100]LISA M M,BONCELET C G.Capacity of the additive steganographic channel.[EB/OL].1999.Available:http://www.eecis.udel.edu/~marvel/.
[101]ETTINGER J M.Steganalysis and game equilibria[J].Lecture Notes in Computer Science,1998,1525:319-328.
[102]MOULIN P,O'SULLIVAN J A.Information theoretic analysis of information hiding[J].IEEE Transaction on Information Theory,March 2003,49:563-581.
[103]MOSKOWITZ I S,KANG M H.Covert channels-Here to stay? Compass'94:9th Annual Conference on Computer Assurance[C].Gaithersburg,MD,USA,1994:235-243.
[104]SHANNON C E.A mathematical theory of communication[J].Bell System Technical Journal.1948,27:379-423 and 623-656.
[105]SHANNON C E.Communication in the presence of noise.Proceedings of the IEEE[C].1984,72(9):1192-1201.
[106]SHANNON C E.Communication theory of secrecy systems[J].Bell System Technical Journal,1949,28(4):656-715.
[107]林代茂.信息安全--系统的理论与技术[M].北京:科学出版社,2008.
[108]钟义信.信息科学原理[M].北京:北京邮电大学出版社,2002.
[109]蒙娜丽莎惊现奇异图像[EB/OL].http://world.huanqiu.com/photo/2007-12/32272.html
[110]林代茂,胡岚,郭云彪,等.广义信息隐藏技术的机理与模型[J].北京邮电大学学报,2005,28(1):1-5.
[111]CHANG C C,LIN C J.LIBSVM:A library for support vector machines[EB/OL].2001.http://www.csie.ntu.edu.tw/?cjlin/libsvm
[112]SMOLA A J,SCH(O|¨)LKOPF B.A tutorial on support vector regression[J].Stat.Comput,2004,14:199-222.
[113]CRANDALL R.Some notes on steganography[EB/OL].1998.http://os.inf.tu-dresden.de /~westfeld/crandall.pdf
[114]BIERBRAUER J,FRIDRICH J.Constructing good covering codes for applications in steganography[EB/OL].2006.http://www.math.mtu.edu/~jbierbra/HOMEZEUGS/ stegocovsurveyOct06,ps
[115]FRIDRICH J,LISONEK P,SOUKAL D.On steganographic embedding efficiency.Information Hiding:8th International Workshop,IH2006[C].Alexandria,VA,USA,2006,4437:282-296.
[116]MUNUERA C.Steganography and error-correcting codes[J].Signal Processing,2007,87(6):1528-1533.
[117]COHEN G D,HONKALA I,LITSYNS,et al.Covering codes[M].Amsterdam:North-Holland /Elsevier.1997.
[118]李晓龙,杨斌.LSB matching的嵌入效率分析[J].南京理工大学学报(自然科学版),2008,32(4).
[119]KUZNETSOVA V,TSYBAKOVB,S.Coding in a memory with defective cells[J].Probl.Inform.Transmission,1974,10:132-138.
[120]HEEGARD C,GAMAL A E.On the capacity of computer memory with defects[J].IEEE Transactions on Information Theory,1983,29(5):731-739.
[121]KHANESAR M A,TESHNEHLAB M,SHOOREHDELI M A.et al.A novel binary particle swarm optimization.15th Mediterranean Conference on Control & Automation[C].Athens,2007:1-6.
[122]http://www.usatoday.com/life/cyber/tech/2001-02-05-binladen,htm
[123]GOLJANM,FRIDRICH J,HOLOTYAKT.New blind steganalysis and its implications.Proc.SPIE,Security,Steganography,and Watermarking of Multimedia contents Ⅷ[C].San Jose,CA.2006,6072:607201.1-607201.13.
[124]LI B,HUANG J W,SHI Y Q.Textural features based universal steganalysis.Security,Forensics,Steganography,and Watermarking of Multimedia Contents X.Proceedings of the SPIE[C].2008,6819:681912-681912-12.
[125]MACQUEEN J B.Some methods for classification and analysis of multivariate observations.Proc.of the 5th Berkeley Symp.on Mathematical Statistics and Probability[C].Berkeley,USA,1967:281-297.
[126]http://www.dpreview.com/gallery/
[127]HSU C W,LIN C J.A comparison of methods for multi-class support vector machines [J].IEEE Transactions on Neural Networks,2002,13(2):415-425.
[128]CHIN K K.Support vector machines applied to speech pattern classification.Master' s thesis[D].University Cambridge,Cambridge,U.K.,1998.
[129]PLATT J C,CRISTIANINI N,SHAWE-TAYLOR J.Large margin DAG' s for multiclass classification[J].In Advances in Neural Information Processing Systems,2000,12:547-553.
[130]SHI Y Q,CHEN C,CHEN W.A Markov process based approach to effective attacking JPEG steganography.Proceedings of the 8th Information Hiding Workshop[C].Alexandria,Virginia,2006:249-264.
[131]WU T F,LIN C J,WENG R C.Probability estimates for multi-class classification by pairwise coupling[J].Journal of Machine Learning Research,2004(5):975-1005.
[132]藤素珍.数理统计学[M].大连:大连理工大学出版社,2005.
[133]BOHME R.Breaking Cauchy model-based JPEGsteganography with first order statistics.Proc.Of 9th ESORICS[C].France,2004:125-140.
[134]DU R,GUTHRIE L E,BUCHY D.Steganalysis with JPEG and GIF images[J].Security,Steganography,and Watermarking of Multimedia Contents,2004,5306:98-104.
[135] KHARRAZI M, SENCAR H T, MEMON N. Performance study of common image steganography and steganalysis techniques [J]. Journal of Electronic Imaging, 2006, 15(4):041104.1 -041104.16.
[136] WANG Y, MOULIN P. Optimized feature extraction for learning-based image steganalysis [J]. IEEE Transactions on Information Forensics and Security, 2007, 2(1):31-45.
[137] PEVNY T, FRIDRICH J. Merging Markov and DCT features for multi-class JPEG steganalysis. Proceedings SPIE, Electronic Imaging, Security, Steganography, and Watermarking of Multimedia Contents IX [C]. San Jose, CA, 2007, 6505:310-314.
[138] DIETTERICH T G. Machine learning research: four current directions [J]. AI Magazine, 1997, 18(4): 97-136.
[139] ZHOU Z H, TANG W. Selective ensemble of decision trees [J]. Lecture Notes in Artificial Intelligence, 2003, 2639:476-483.
[140] BREIMAN L. Bagging predictors [J]. Machine Learning, 1996, 24(2):123-140.
[141] BAUER E, KOHAVI R. An empirical comparison of voting classification algorithms: Bagging, boosting, and variants [J]. Machine Learning, 2001, 36(1-2):105-139.
[142] BREIMAN L. Random forest [J]. Machine Learning, 2001, 45(1):5-32.
[143] FREUND Y, SCHAPIRE R E. A decision-theoretic generalization of on-line learning and an application to boosting. Proceedings of the 2nd European Conference on Computational Learning Theory [C]. Barcelona, Spain, 1995:23-37.
[144] BREIMAN L. Bias, variance, and arching classifiers. Technical Report 460 [R]. Statistics Department, University of California, Berkeley, CA. 1996.
[145] FRIEDMAN J, HASTIE T, TIBSHIRANI R. Additive logistic regression: A statistical view of boosting [J]. The Annals of Statistics, 2000, 28(2):337-407.
[146] WOLPERT D H, MACREADY W G. No free lunch theorems for optimization [J]. IEEE Transactions on Evolutionary Computation, 1997, 1(1):67-82.
[147] MILLER D J, UYAR H S. A mixture of experts classifier with learning based on both labelled and unlabelled data. Advances in Neural Information Processing Systems 9. Cambridge [C]. MA: MIT Press. 1997:571-577.
[148] BLUM A, MITCHELL T. Combining labeled and unlabeled datawith co-training. Proceedings of the 11th annual conference on Computational Learning Theory [C]. Wisconsin, USA, 1998:92-10.
[149] GOLDMAN S, ZHOU Y. Enhancing supervised learning with unlabeled data. Proceedings of the 17th International Conference on Machine Learning [C]. California, USA, 2000:327-33.
[150] ZHOU Z H, LI M. Tri-training: Exploiting unlabeled data using three classifiers [J]. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(11):1529-1541.