Computer Science ›› 2026, Vol. 53 ›› Issue (7): 381-396.doi: 10.11896/jsjkx.250600196
• Information Security • Previous Articles Next Articles
CHEN Quantao, ZHANG Yangsen, WANG Pu, GUO Yalong
CLC Number:
| [1]SINGH S,SINGH S,KRAUS S,et al.Characterizing generative artificial intelligence applications:Text-mining-enabled technology roadmapping[J].Journal of Innovation and Knowledge,2024,9(3):100531. [2]LI Z,HUANG C,QIU W.An intrusion detection method combining variational auto-encoder and generative adversarial networks[J].Computer Networks,2024,253:110724. [3]CHEN J Y,XI C K,ZHENG H B,et al.A Survey on the Security of Multimodal Large Language Models [J].Journal of Computer Science,2025,52(7):315-341. [4]GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Ge-nerative adversarial nets[C]//Advances in Neural Information Processing Systems.2014. [5]MA Z,ZHANG Y,JIA G,et al.Efficient Diffusion Models:A Comprehensive Survey from Principles to Practices [J].arXiv:2410.11795,2024. [6]HO J,JAIN A,ABBEEL P.Denoising Diffusion ProbabilisticModels [J].arXiv:2006.11239,2020. [7]LUKOIANOV A,DE OCÁRIZ BORDE H S,GREENEWALD K,et al.Score Distillation via Reparametrized DDIM[C]//Proceedings of Advances in Neural Information Processing Systems.New York:Curran Associates Inc.,2024:26011-26044. [8]CHEN M S,MEI S,FAN J Q,et al.Opportunities and challenges of diffusion models for generative AI[J].National Science Review,2024,11(12):nwae348. [9]JIANG Y,YANG Y,YIN J L,et al.A survey on security and privacy risks in large language models[J].Journal of Computer Research and Development,2025,62(8):1979-2018. [10]ZHANG X L,QU X Y,XIE J F,et al.Overview of Artificial Intelligence Generated ContentTechnologies [J/OL].Big Data Research,2025:1-37.[2025-08-14].https://link.cnki.net/urlid/10.1321.G2.20250408.1439.004. [11]HAO Y H.Analysis and Governance of Artificial Intelligence Security Risks [J].Journal of China Academy of Electronics and Information Technology,2020,15(6):501-505. [12]ZHU B,MU N,JIAO J,et al.Generative AI Security:Challenges and Countermeasures [J].arXiv:2402.12617,2024. [13]FERRAG M A,ALWAHEDI F,BATTAH A,et al.Generative AI in Cybersecurity:A Comprehensive Review of LLM Applications and Vulnerabilities [J].Internet of Things and Cyber-Physical Systems,2025,5:1-46. [14]SANDMANN S,HEGSELMANN S,FUJARSKI M,et al.Benchmark evaluation of DeepSeek large language models in clinical decision-making[J].Nature Medicine,2025,31(8):2546-2549. [15]HU T,KYRYCHENKO Y,RATHJE S,et al.Generative language models exhibit social identity biases[J].Nature Computational Science,2025,5:65-75. [16]CANCELA-OUTEDA C.The EU's AI act:A framework for collaborative governance[J].Internet of Things,2024,27:101291. [17]HOWELLM D.Generative artificial intelligence,patient safetyand healthcare quality:A review[J].BMJ Quality & Safety,2024,33(11):748-754. [18]UDDIN M,IRSHAD M S,KANDHRO I A,et al.Generative AI revolution in cybersecurity:a comprehensive review of threat intelligence and operations[J].Artificial Intelligence Review,2025,58(8):236. [19]KHAN N,NGUYEN T,BERMAK A,et al.Unmasking Syn-thetic Realities in Generative AI:A Comprehensive Review of Adversarially Robust Deepfake Detection Systems [J].arXiv:2507.21157,2025. [20]YAN Z,ZHANG Y,FAN Y,et al.UCF:Uncovering Common Features for Generalizable Deepfake Detection[C]//2023 IEEE/CVF International Conference on Computer Vision(ICCV).Piscataway,NJ:IEEE,2023:22355-22366. [21]PEREZ E,HUANG S,SONG F,et al.Red Teaming Language Models with Language Models [J].arXiv:2202.03286,2022. [22]LIU Y,JIA Y,GENGR,et al.Formalizing and Benchmarking Prompt Injection Attacks and Defenses[C]//Proceedings of the 33rd USENIX Security Symposium.Philadelphia,PA:USENIX Association,2024:1831-1847. [23]KANG D,LI X,STOICA I,et al.Exploiting programmatic behavior of LLMs:Chain-of-thought injections[C]//2024 IEEE Symposium on Security and Privacy Workshops.IEEE,2024:132-143. [24]LEI T,ZHANG Y,WANG X,et al.Jailbreaking black box large language models in twenty queries[C]//Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security.New York:ACM,2024:2423-2437. [25]HUANG H,ZHAO Z Y,BACKES M,et al.Composite Back-door Attacks Against Large Language Models[C]//Proceedings of the Findings of the Association for Computational Linguistics:NAACL 2024.Mexico City:Association for Computational Linguistics,2024:1459-1472. [26]ZHAO S,JIA M H Z,GUO Z L,et al.A Survey of Recent Backdoor Attacks and Defenses in Large Language Models[J].ar-Xiv:2406.06852,2024. [27]QIN Z,ZHUANG T M,ZHU G S,et al.A Survey of Security Attacks and Defense Strategies for Artificial Intelligence Models [J].Journal of Computer Research and Development,2024,61(10):2627-2648. [28]JIAO W,HUANG J,WANG W,et al.ParroT:Translating du-ring chat using large language models tuned with human translation and feedback[C]//Proceedings of the Findings of the Association for Computational Linguistics:EMNLP 2023.Association for Computational Linguistics,2023:15009-15020. [29]LIU Y,WU C,YUAN K,et al.Targeted model extraction from API-based ML services[C]//Proceedings of the 2024 IEEE Symposium on Security and Privacy.IEEE,2024:1843-1858. [30]PAN X D,ZHANG M,JI S L,et al.Privacy risks of general-purpose language models[C]//Proceedings of the 41st IEEE Symposium on Security and Privacy(SP).Piscataway,NJ:IEEE,2020:1314-1331. [31]SONG C Z,RAGHUNATHAN A.Information leakage in embedding models[C]//Proceedings of the 27th ACM SIGSAC Conference on Computer and Communications Security.New York:ACM,2020:377-390. [32]LI H,XU M S,SONG Y Q.Sentence Embedding Leaks More Information than You Expect:Generative Embedding Inversion Attack to Recover the Whole Sentence [J].arXiv:2305.03010,2023. [33]ZHANG R,HIDANO S,KOUSHANFAR F.Text Revealer:Private Text Reconstruction via Model Inversion Attacks against Transformers [J].arXiv:2209.10505,2022. [34]SHEN X Y,CHEN Z Y,BACKES M,et al.“Do Anything Now”:Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models [J].arXiv:2308.03825,2023. [35]LI H,GUO D D,FAN W,et al.Multi-step Jailbreaking Privacy Attacks on ChatGPT [J].arXiv:2304.05197,2023. [36]YANG A,YANG TA.Social Dangers of Generative Artificial Intelligence:Review and Guidelines[C]//Proceedings of the 25th Annual International Conference on Digital Government Research.2024:654-658. [37]CHUA J,LI Y,YANG S Y,et al.AI Safety in Generative AI Large Language Models:A Survey [J].arXiv:2407.18369,2024. [38]BU Z,ZHANG X,ZHA S,et al.Pre-training Differentially Private Models with Limited Public Data[C]//Proceedings of the 37th Conference on Neural Information Processing Systems(NeurIPS 2024).Curran Associates Inc.,2024:94652-94683. [39]NAHID M M H,HASAN S B.SafeSynthDP:Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy [J].arXiv:2412.20641,2024. [40]WANG H,XU Q,ZHANG Q H,et al.LFDP:Low-Frequency Information Fusion for Differential Privacy Robustness Enhancement [J].Journal of Information Security,2025,10(1):47-60. [41]WU X W,GONG L,XIONG D Y.Adaptive differential privacy for language model training[C]//Proceedings of the First Workshop on Federated Learning for Natural Language Processing.Association for Computational Linguistics,2022:21-26. [42]LU X Z,LIU Z H,XIAO L,et al.Reinforcement Learning-Based Personalized Differentially Private Federated Learning[J].IEEE Transactions on Information Forensics and Security,2025,20:465-477. [43]AZIZ R,BANERJEE S,BOUZEFRANE S.Privacy preservingfederated learning:a novel approach for combining differential privacy and homomorphicencryption[C]//Information Security Theory and Practice:14th IFIP WG 11.2 International Confe-rence,WISTP 2024.Springer,2024:162-177. [44]BRAKERSKI Z,VAIKUNTANATHAN V.Efficient Fully Homomorphic Encryption from(Standard) LWE [EB/OL].(2011-06-26) [2025-05-21].https://eprint.iacr.org/2011/344. [45]GUO K Y,HAN Y L,WU R M.Revocable Hierarchical Attri-bute-Based Encryption Scheme Based on RLWE [J].Information Technology and Network Security,2021,40(8):9-16. [46]DOBRAUNIG C,GRASSI L,HELMINGER L,et al.Pasta:a case forhybrid homomorphic encryption[C]//Proceedings of the 33rd USENIX Security Symposium.Berkeley:USENIX Association,2024:1-18. [47]MATSUMOTO M,NOZAKI A,TAKASE H,et al.TFHE-SBC:Software Designs for Fully Homomorphic Encryption over the Torus on Single Board Computers [J].arXiv:2503.02559,2025. [48]CHEN D,QU H,XU G.AegisFL:Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated Learning[C]//Proceedings of the 41st International Conference on Machine Learning.PMLR,2024:7207-7219. [49]RIAZ R,HAN G,SHAUKAT K,et al.A novel ensemble Wasserstein GAN framework for effective anomaly detection in industrial internet of things environments [J].Scientific Reports,2025,15(1):26786. [50]CHEN L,JIANG H,WANG L,et al.Generative adversarialsynthetic neighbors-based unsupervised anomaly detection [J].Scientific Reports,2025,15:16. [51]LIGUORI A,RITACCO E,PISANI F S,et al.Robust anomaly detection via adversarial counterfactual generation[J].Know-ledge and Information Systems,2024,66:7437-7468. [52]FANG Q Q,SU Q L,LYU W X,et al.Boosting Fine-Grained Vi-sual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2025:16532-16540. [53]SUN H L,HUANG Y,HAN L S,et al.MTS-DVGAN:Anomaly detection in cyber-physical systems using a dual variational generative adversarial network[J].Computers & Security,2024,139:103570. [54]ZHAO Y.Anomaly Hybrid:A Domain-agnostic Generative Fra-mework for General Anomaly Detection[J].arXiv:2504.04340,2025. [55]CAO Y,XU X,SUN C,et al.Towards generic anomaly detection and understanding:large-scale visual-linguistic model(GPT-4V) takes the lead [J].arXiv:2311.02782,2023. [56]FERETZAKIS G,VERYKIOS V S.Trustworthy AI:Securing sensitive data in large language models [J].arXiv:2409.18222,2024. [57]STOCKS M.IBAC mathematics and mechanics:The case for‘integer based access control' of data security in the age of AI and AI automation [J].arXiv:2410.19021,2024. [58]VIZGIRDA V,ZHAO R,GOEL N.SocialGenPod:Privacy-friendly generative AI social web applications with decentralised personal data stores [C]//Proceedings of the ACM Web Conference 2024 Companion.New York:ACM,2024:1174-1178. [59]LONGPRE S,MAHARI R,CHEN A,et al.The Data Prove-nance Initiative:A large scale audit of dataset licensing & attribution in AI [J].arXiv:2310.16787,2023. [60]XIE Y,SONG J,WANG H,et al.Training data provenance verification:Did your model use synthetic data from my generative model for training? [J].arXiv:2503.09122,2025. [61]Coalition for Content Provenance and Authenticity.Content Authenticity Initiative [EB/OL].[2025-05-12].https://c2pa.org/. [62]BELGODERE B M,DOGNIN P L,IVANKAY A,et al.Auditing and generating synthetic data with controllable trust trade-offs[J].IEEE Journal on Emerging and Selected Topics in Circuits and Systems,2023,14:773-788. [63]MIT MEDIA LAB.Data provenance and consent in generative AI [EB/OL].(2024-12-31) [2025-05-12].https://mit-genai.pubpub.org/pub/uk7op8zs. [64]ZHANG C Y,HU M W,LI W H,et al.Adversarial Attacks and Defenses on Text-to-Image Diffusion Models:A Survey[J].ar-Xiv:2407.15861,2024. [65]GAO T,YAO X,CHEN D.SimCSE:SimpleContrastive Learning of Sentence Embeddings [C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.Association for Computational Linguistics,2021:6894-6910. [66]WU L,LI S,HSIEH C,et al.Stochastic shared embeddings:Data-driven regularization of embedding layers[C]//Proceedings of the 33rd International Conference on Neural Information Processing Systems.Red Hook,NY:Curran Associates Inc.,2019:24-33. [67]YANG W L,YANG J,GUO Y,et al.Defensive Dual Masking for Robust Adversarial Defense[J].arXiv:2412.07078,2024. [68]FRANCHI G,LAURENT O,LEGUERY M,et al.Make me a BNN:A simple strategy for estimating Bayesian uncertainty from pre-trained models[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE Computer Society,2024:12194-12204. [69]XU X,LIU Z,KOFFAS S,et al.BAN:Detecting Backdoors Activated by Adversarial Neuron Noise[C]//Proceedings of the 38th Conference on Neural Information Processing Systems.Cambridge:MIT Press,2024:114348-114373. [70]PAN X D,ZHANG M,SHENG B N,et al.Hidden trigger backdoor attack on NLP models via linguistic style manipulation[C]//Proceedings of the 31st USENIX Security Symposium.Berkeley:USENIX Association,2022:3611-3628. [71]SUN H,ZHONG Q,QI M,et al.Towards robust speech mo-dels:Mitigating backdoor attacks via audio signal enhancement and fine-pruning techniques[J].Mathematics,2025,13(6):984. [72]LIN W,LIU L,WEI S,et al.Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness[C]//Proceedings of the 38th Conference on Neural Information Processing Systems.Cambridge:MIT Press,2024:42097-42122. [73]SUN Z,CONG T,LIU Y,et al.PEFTGuard:Detecting backdoor attacks against parameter-efficient fine-tuning [C]//Procee-dings of the 2025 IEEE Symposium on Security and Privacy.IEEE,2025:1713-1731. [74]SHAH H,PARK S M,ILYAS A,et al.ModelDiff:A framework for comparing learning algorithms[C]//Proceedings of the 39th International Conference on Machine Learning.PMLR,2022:19482-19500. [75]BAI Y,XING G,WU H,et al.Backdoor attack and defense on deep learning:A survey[J].IEEE Transactions on Computatio-nal Social Systems,2024,11(2):404-434. [76]KIRSCHENBAUER J,GEIPING J,WEN Y,et al.A watermark for large language models [C]//Proceedings of the 40th International Conference on Machine Learning.PMLR,2023:17061-17084. [77]DATHATHRI S,SEE A,GHAISAS S,et al.Scalable water-marking for identifying large language model outputs[J].Nature,2024,634(8035):818-823. [78]REN H,XU H,LIU Y,et al.A Robust Semantics-Based Watermark for Large Language Models Against Paraphrasing[C]//Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.Singapore:Association for Computational Linguistics,2023:7199-7213. [79]BALDASSIN F B,NGUYEN H H,CHANG C C,et al.Cross-Attention Watermarking of Large Language Models[C]//Proceedings of the 2024 IEEE International Conference on Acoustics,Speech and Signal Processing.IEEE,2024:1-5. [80]MA R,GUO M,LI Y,et al.PiGW:A plug-in generative watermarking framework [J].arXiv:2403.12053,2024. [81]LI Z T,MENG X F,WANG L X,et al.A Survey on Machine Unlearning [J].Journal of Software,2025,36(4):1637-1664. [82]JANG J,YOON D,YANG S,et al.Knowledge unlearning for mitigating privacy risks in language models[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.Stroudsburg,PA:ACL,2023:14389-14408. [83]CHEN J,YANG D.Unlearn what you want to forget:Efficient unlearning for LLMs[C]//Proceedings of the 28th Conference on Empirical Methods in Natural Language Processing.Stroudsburg,PA:ACL,2023:12041-12052. [84]MAINI P,FENG Z,SCHWARZSCHILD A,et al.TOFU:ATask of Fictitious Unlearning forLLMs [J].arXiv:2401.06121,2024. [85]ZHANG R,LIN L,BAI Y,et al.Negative Preference Optimization:From Catastrophic Collapse to Effective Unlearning [J].arXiv:2404.05868,2024. [86]TIAN B,LIANG X,CHENG S,et al.To forget or not?Towards practical knowledge unlearning for large language models[C]//Proceedings of the 29th Conference on Empirical Methods in Natural Language Processing.Stroudsburg,PA:ACL,2024:1524-1537. [87]MURESANU A,THUDI A,ZHANG M R,et al.Unlearnable Algorithms for In-context Learning [J].arXiv:2402.00751,2024. [88]CHOI D,NA D.Distribution-Level Feature Distancing for Machine Unlearning:Towards a Better Trade-off Between Model Utility and Forgetting [C]//Proceedings of the AAAI Confe-renceon Artificial Intelligence.2025:2536-2544. [89]WANG M R,YAO Y Z,XI Z K,et al.Security Analysis of Large Model Content Generation Based on Knowledge Editing [J].Journal of Computer Research and Development,2024,61(5):1143-1155. [90]LIU C Y,WANG Y,FLANIGAN J,et al.Large Language Mo-del Unlearning via Embedding-Corrupted Prompts [J].arXiv:2406.07933,2024. [91]WU X W,LI J Z,XU M H,et al.DEPN:Detecting and editing privacy neurons in pretrained language models[C]//Proceedings of the 28th Conference on Empirical Methods in Natural Language Processing.Stroudsburg,PA:ACL,2023:2875-2886. [92]VENDITTI D,RUZZETTI E S,XOMPERO G A,et al.Enhancing Data Privacy in Large Language Models through Private Association Editing [J].arXiv:2406.18221,2024. [93]LIU S,ZHENG C,WANG Y,et al.Unsupervised detection of adversarial examples with local outlier factors[J].IEEE Transactions on Information Forensics and Security,2024,19:5805-5818. [94]WANG Y,LI H,HAN X,et al.Do-Not-Answer:A Dataset for Evaluating Safeguards in LLMs [J].arXiv:2308.13387,2023. [95]ZHANG M,PAN X D,YANG M.JADE:A Linguistics-based Safety Evaluation Platform for Large Language Models[J].ar-Xiv:2308.07814,2023. [96]LIANG P,BOMMASANI R,LEE T,et al.Holistic evaluation of language models[J/OL].Transactions on Machine Learning Research,2023.https://doi.org/10.48550/arXiv.2211.09110. [97]HUANG R,WANG X,LIZ,et al.Guided Bench:Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods [J].arXiv:2502.,202516903. [98]WANG Z,ZHANG G,YANG K,et al.Interactive Natural Language Processing [J].arXiv:2305.13246,2023. [99]中国信息通信研究院,中国科学院计算技术研究所.大模型治理蓝皮报告:从规则走向实践[R].北京:中国信通院,2023-11-24. [100]LEE K,KIM H,WHANG J J.SAIF:A comprehensive framework for evaluating the risks of generative AI in the public sector [J].arXiv:2501.08814,2025. |
| [1] | HUANG Yilu, HE Xingxing, REN Ruibin, ZENG Wenqiang. Collaborative Adversarial Training Defense Framework for Network Traffic Classification Based on Ensemble Learning and Weight Constraint [J]. Computer Science, 2026, 53(7): 397-405. |
| [2] | DING Yan, DING Hongfa, YU Muran, JIANG Heling. Survey of Backdoor Attacks and Defenses on Graph Neural Network [J]. Computer Science, 2026, 53(3): 1-22. |
| [3] | ZHANG Wanyou, SONG Lipeng. Cloud Email Defense Resource Allocation Method Based on User Behavior [J]. Computer Science, 2026, 53(2): 442-453. |
| [4] | WEN Zerui, JIANG Tian, HUANG Zijian, CUI Xiaohui. Section Sparse Attack:A More Powerful Sparse Attack Method [J]. Computer Science, 2026, 53(1): 323-330. |
| [5] | ZHENG Xu, HUANG Xiangjie, YANG Yang. Reversible Facial Privacy Protection Method Based on “Invisible Masks” [J]. Computer Science, 2025, 52(5): 384-391. |
| [6] | CHANG Ningyuan, HUANG Ting, ZHANG Huang. Demand Response Scheme for Low Voltage Users Based on Light Weight Blockchains [J]. Computer Science, 2025, 52(11A): 250200125-8. |
| [7] | CHEN Kang, LIN Jianhan, LIU Yuanjie. Survey on Image Deblurring Algorithms [J]. Computer Science, 2025, 52(11): 98-112. |
| [8] | WANG Liuyi, ZHOU Chun, ZENG Wenqiang, HE Xingxing, MENG Hua. High-frequency Feature Masking-based Adversarial Attack Algorithm [J]. Computer Science, 2025, 52(10): 374-381. |
| [9] | YUAN Mengjiao, LU Tianliang, HUANG Wanxin, HE Houhan. Benign-salient Region Based End-to-End Adversarial Malware Generation Method [J]. Computer Science, 2025, 52(10): 382-394. |
| [10] | WANG Chundong, LI Quan, FU Haoran, HAO Qingbo. Face Anti-spoofing Method with Adversarial Robustness [J]. Computer Science, 2024, 51(6A): 230400022-7. |
| [11] | GUO Yuqi, LI Dongyang, YAN Bin, WANG Linyuan. Black-box Adversarial Attack Methods on Modulation Recognition Neural Networks Based onSignal Proximal Linear Combination [J]. Computer Science, 2024, 51(10): 425-431. |
| [12] | LI Kun, GUO Wei, ZHANG Fan, DU Jiayu, YANG Meiyue. Adversarial Malware Generation Method Based on Genetic Algorithm [J]. Computer Science, 2023, 50(7): 325-331. |
| [13] | HUANG Feihu, SHUAI Jianbo, PENG Jian. Collaborative Recommendation Based on Curriculum Learning and Graph Embedding [J]. Computer Science, 2023, 50(11A): 221100030-8. |
| [14] | RONG Baojun, ZHENG Zhaohui. FL_Raft:Election Consensus Programme Based on Federated Learning Model [J]. Computer Science, 2023, 50(11): 364-373. |
| [15] | CAO Linxiao, LIU Jia, ZHU Yifei, ZHOU Haoquan, GONG Wei, YU Weihua, LI Chaoyou. Ventilator and Sedative Management in Networked ICUs Based on Federated Learning [J]. Computer Science, 2023, 50(10): 165-175. |
|
||
Home