Nicholas Carlini による敵対的サンプル論文リストの継続版です。2025-09-15 以降に arXiv に投稿された論文を対象としています。元のリスト（13,697 件）で学習した TF-IDF + ロジスティック回帰の分類器（ホールドアウト AUC 0.998）でスコアが 40% 以上の論文を掲載し、arXiv ID の年月ごとにまとめています。
総数: 3477 件
最終更新: 2026-11-11.

直近1か月

2026-11（84 件）

• [100%] Black-Box Adversarial Example Attacks on Machine Learning based Election Systems
  Subek Acharya; Syed Ayon; Khaleque Md Aashiq Kamal; Alina Barnett; Surya Eada; Kaleel Mahmood
• [100%] Adversarial Robustness of Kernel Machines: A Comprehensive Analysis
  Rahul Kumar Yadav; Tunir Ghosh; Sudhendu Ahir; Parthe Pandit; Arjun Bhagoji
• [99%] VIPA: View-Invariant Projector-Based Adversarial Attack
  Jiyu Han; Qingyue Deng; Bingyao Huang
• [98%] GARD: Gradient-Guided Adversarial Representation Defense against Backdoors in Multimodal Contrastive Learning Models
  Yuhong Wang; Yujun Cai; Lei Feng; Songze Li
• [97%] Structured Confidence Perturbation via Fisher Geometry for Adversarial Training
  Chenlong Wei; Hanling Wang; Chong Zhang; Qinkai Yu; Fangyu Wu; Xiaobo Jin
• [96%] Anchored Rank-Adversarial Fine-Tuning Pretrained Visual Place Recognition Models
  Mostafa Kira; Bader Rasheed; Manuel Mazzara
• [96%] On Lipschitz Explosion in Deep Neural Networks with Normalization: Consequences for Optimization and Adversarial Robustness
  Ashkan Soleymani; Reyhaneh Hosseinpourkhoshkbari; Hadi Daneshmand; Patrick Jaillet
• [95%] RL-ATTACK: A Generalized Black-Box Adversarial Attack on Language Models via Reinforcement Learning
  Taikun Chen; Yue Zhang; Wei Qian; Hui Fang
• [93%] Robust Deep Prototype Classifiers via Lipschitz Training
  Adia Khalid Khan; Lukas Gehring; Benjamin Paaßen
• [93%] AnyBreak: Towards Jailbreaking Any T2I Model for Any Concept
  Qi Lu; Zehui Guo; Yucheng Zhao; Zijing Li; Chuhan Song; Wenrui Zhu
• [91%] Adversarial Robustness Is Not Zero-Day Generalization: A Controlled Evaluation of Flow-Based Intrusion Detectors on Corrected CIC-IDS2017
  Abdulhamid Zaro
• [89%] SNAPRAG: Cost-Efficient Knowledge Extraction Attack on RAG Systems via Adversarial Perturbations
  Melih Coşğun; Mehmet Emre Gürsoy; Alptekin Küpçü; Sinem Sav
• [86%] Adversarial Robustness of Retrieval-Based Fact-Checking: Detecting and Mitigating Evidence Contamination
  Alamgir Munir Qazi; John P. McCrae; Jamal Abdul Nasir
• [84%] Adversarial robustness does not entail human-aligned categorization
  Itay Reznik; Raz Lapid; Moshe Sipper; Tal Golan
• [84%] Procedural Adversarial Learning
  Jack Nugent; Jia Deng
• [80%] The Blind Spots of Detection: Adversarial Perturbation Attacks against Watchdogs in Distributed LLM Inference
  Siu Wai Shi; Xiaochen Zhu; Xinjian Luo; Keke Huang; Bingxue Zhang; Xiaofeng Gao
• [80%] Towards Fine-grained and Robust Detection of Human-AI Co-authorship
  Ziruo Zhao; Jie Fu; Wendy Hui Wang; Zining Zhu
• [80%] JevBreak: Your Model, Their Decision
  Nitin Aravind Birur; Divyanshu Kumar; Sahil Agarwal; Prashanth Harshangi
• [80%] Robustness Verification against Patch Attacks via Group-Lasso Semidefinite Relaxation
  Yukina Nakagawa; Takami Sato; Ken Kobayashi; Kazuhide Nakata
• [80%] Catastrophic Overfitting is Weight Drift the Training Loss Cannot See
  Chao Pan
• [80%] A Bag of Tricks for Defending Deep Learning-based Face Recognition Pipelines against Backdoor Attacks
  Quentin Le Roux; Marti Jimenez; Yannick Teglia; Philippe Loubet Moundi
• [80%] Scaling Adaptive Prompt Injection Attacks with Agent Swarms
  Alexey Kurakin; Vishal Karande; Alex Bie; Chongyang Shi; Shuang Song; Saeed Mahloujifar; Abdullatif Köksal; Jamie Hayes; Juliette Pluto; Yinghao Sun; Kamalika Chaudhuri
• [79%] Addition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language Models
  Hamid Dashtbani; Alexandra Dmitrienko
• [78%] ScrambleMark: Zero-Query Watermark-Agnostic Black-Box Evasion of Modern Speech Watermarking
  Binhao Ma; Weikang Ding; Hanqing Guo; Wenwei Zhao; Xiaowen Li; Leah Ding; Zhuo Lu; Rui Duan
• [76%] HideOut – User Protection Against Localization with Throughput Guarantees in Mobile Networks
  Navidreza Asadi; Michele Guardiani; Wolfgang Kellerer; Jafar Aco Mohammadi
• [76%] Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks
  Rongting Zhang; Martin Bertran; Sandeep Avula; Chia-Jung Lee; Vanessa Murdock
• [76%] Attacking Slide Puzzle CAPTCHAs Based on Time and Space Generative Adversarial Networks
  Rui Guo; Xuelian Xie; Botao Xu; Kesheng Liu; Wenxian Wang; Haizhou Wang
• [76%] FocusBranch: Combinatorial Branch-and-Bound for $\ell_0$ Neural Network Robustness Verification
  Renwei Deng; Yang He; Linyi Li; Yuepeng Wang
• [75%] The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents
  Geyuan Wang; Shunyu Liu; Siyuan Liang; Chenyang Lyu; Dacheng Tao
• [74%] The Devil is in the Context: Nine Dimensions of Prompt Injection Attacks
  Jiamin Chang; Kristina Nikolić; Rishi Sharma; Giovanni Cherubin; Vasilios Mavroudis; Jose Sanchez Vicarte; Arnav Garg; Hammond Pearce; Andrew Paverd; Ahmed Salem
• [74%] BrainwashedLLM: Jailbreaking via Automated Adversarial Chain of Thoughts Discovery
  Masoud Poorghaffar Aghdam; Göktuğ Serdar Yıldırım; Sinem Sav
• [74%] RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples
  Chao Zhou; Shenghua He; Jiaxin Mo; Qiangguo Yu; Fengchuang Xing
• [74%] Should We Pay This Much for Robustness? Efficient Proxy Certificates with Marginal Guarantees
  Soroush H. Zargarbashi; Mohammad Sadegh Akhondzadeh; Aleksandar Bojchevski
• [72%] Systematic Evaluation of Robustness in Fine-tuned Models
  Angela John; Hamayoon Behmanush
• [71%] Beyond $L_\infty$-Norm Sets: Synthesizing Interpretable Non-Uniform Uncertainty Sets for Evaluation-Time State-Adversarial Robustness
  Xulin Chen; Ruipeng Liu; Garrett E. Katz
• [70%] Zero-Query Transferable Pretend Benign Attacks with Amortized Online Generation for Cooperative Perception
  Hongwei Lin; Xun Huang; Chenglu Wen; Cheng Wang
• [69%] GuardrailAgent: An Agentic Framework for Jailbreak Defense
  Tianze Chang; Junjie Chu; Yixin Wu; Michael Backes; Yang Zhang
• [68%] Certifying Graph Neural Networks Against Label and Structure Poisoning
  Lukas Gosch; Xichuan Chen; Yan Scholten; Stephan Günnemann
• [67%] When appearance and motion disagree: evaluating class–motion consistency against disguised uncrewed surface vessels
  Jon Reifschneider
• [67%] XposedMIA: Exploiting Explainable Artificial Intelligence (XAI) for One-Shot Membership Inference Attacks
  Omar Hamdache; Serdar Kara; Kıvanç Kuzey Dikici; Abdullah Çağlar Öksüz; Anisa Halimi; Erman Ayday; Sinem Sav
• [66%] Data Manipulation Attacks Against Machine Learning Integrated Cyber-Physical Systems
  Soyon Choi; Scott Alfeld; Meiyi Ma
• [65%] Pop Goes the Verifier: Phoneme-Targeted Data Poisoning of Voice Liveness Detection
  Eshaq Jamdar; Amith Kamath Belman
• [65%] Location Matters: Sparse Latent-Variance Attacks for Face Privacy against Diffusion Personalization
  Shuting Yang; Shuxin Li; Linyan Dai; Xinwei Zhang; Dong Huang; Renyang Liu; See-Kiong Ng
• [60%] RGDM: Robust Graph Diffusion Model
  Yancheng Wang; Ping Li; Dongfang Sun; Yingzhen Yang
• [58%] Spoofing the Latent State: Imperceptible Goal-Image Attacks Derail Planning in LeWorldModel
  Kunal Bhosikar; Nicole Meng; Charu Sharma; Yingjie Lao
• [58%] Interactive Backdoor Attacks in LLM-Based Proactive Dialogue Systems
  Zhiyang Xia; Yuming Shang; Xi Zhang
• [56%] CloakFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource Exhaustion
  Li Zheng; Simin Chen
• [55%] Homeopathic Learning: Diluting poisoned fine-tuning data can strengthen its effect
  Matt Clarke; Jan Dubiński; James Chua; Simon Schrodi; Owain Evans; Alex Cloud
• [55%] BAPLe++: Cross-Model Transferability and Prompt-Level Defense of Backdoors in Medical Foundation Models
  Ufaq Khan; Umair Nawaz; Satyajit Tourani; Awais Rauf; Fahad Shamshad; Asif Hanif; Rao Muhammad Anwer; Muhammad Haris Khan; Mohammad Yaqub
• [55%] Chatter Attack: Resource Consumption Attack for Large Language Models
  Yibo Miao; Yichuan Cao; Xiao-Shan Gao; Yinpeng Dong
• [55%] StealthyPoison: Manipulating LLM Agent Behavior through Procedural Poisoning of Third-Party Skills
  Jingfen Qiao; Rui Li; Shuaiqun Pan; Olga Gadyatskaya; Andrew Yates; Evangelos Kanoulas
• [54%] Step-Zero Attack: Agent Safety Before Observability
  Tian Qin; Yuhang Jiang; Junzhe Chen; Lit Sin Tan; Lijie Wen
• [54%] Timing is Everything: Inferring Temporal Membership in Continually Updated Models
  Jie Fu; Xiangpeng Deng; Yuan Hong; Wendy Hui Wang
• [54%] JailBound: FOL-Guided Jailbreak Evaluation for Exploring LLM Behavioral Boundaries
  Fazong Wu; Xin Wang; Ming Yang; Zhenyong Zhang; Xiaoming Wu
• [54%] EVAX: Towards a Practical, Pro-active & Adaptive Architecture for High Performance & Security
  Samira Mirbagher Ajorpaz; Daniel Moghimi; Jeffrey Neal Collins; Gilles Pokam; Nael Abu-Ghazaleh; Dean Tullsen
• [53%] Understanding Backdoor Attacks in Scene Graph Generation via Global Context Pathway
  Xiaoguang Chang; Tuo Chen; Chengze Jiang; Teng Wang; Changyin Sun
• [53%] I Think, Therefore I Attack: Evaluating Thought Injection Attacks on Reasoning Agents
  Parth Illendula; Garik Livingston; Zain Shamsi; Ravi Srinivasan; Alex Liu
• [52%] Debate to Deceive: Poisoning LLM's Fact-Checking via Game-Theoretic Multi-Agent Debate
  Liting Huang; Huizhi Liang; Yi Lei; Xingjun Ma; Varun Ojha
• [50%] The Long Con on the Web: Earn-then-Exploit Fraud Attacks against Coding Agents
  Xingling Xu; Zhengwei Jiang; Zheng Zhi; Fangming Dong; LingJia Guo; Wei Dong; Chunyan Ma; Jun Jiang
• [50%] Beyond Prompt Injection: The Tool Update Gap in LLM Agent Security
  Shiyu Kan; Yue Qi; Yufei Han; Xinjian Luo; Guojun Xiong; Xiaofeng Gao
• [50%] Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs
  Zihao Feng; Qingzhao Zhang; Chunyu Xia; Bo Yu; Z. Morley Mao; Ramesh Govindan
• [49%] J-Anchor: Defending Against Prefill Attacks via J-Space Selective Refusal Restoration
  Running Yang; Beidi Zhao; Xiaoxiao Li
• [47%] TERM: Target-Free Jailbreak Defense via Entropy-Guided Residual Modulation
  Yunkai Dang; Wanyu Zhang; Meiyi Zhu; Qi Fan; Tianyu Ding; Wenbin Li
• [46%] Improving Context-Shift Robustness of Convolutional Networks via Context-Regularized Cross-Entropy
  Jinen Setpal; Chaoyue Liu
• [46%] Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks
  Zhitao He; Chi Him Zhang; Chengru Han; Yi R Fung
• [46%] When Experience Becomes a Backdoor: Poisoning Self-Evolving LLM Agents via Failure-Aware Task Optimization
  Minhua Lin; Zongyu Wu; Hanqing Lu; Xianfeng Tang; Xiang Zhang; Qi He; Suhang Wang
• [45%] Attack Injection to Vehicle Reactions: Extensible Closed-Loop Adversarial Evaluation Framework
  Mohamed Gaber; Tahsin Wahid; Mohammad Mamun; Salimur Choudhury
• [45%] Lipschitz-Controlled Flow Matching for Robust Image Restoration
  Sedjro Salomon Hotegni; Konstantin Sonntag; Paul-Christian Bürkner; Sebastian Peitz
• [44%] ErosionBench: Probing Alignment Decay in Enterprise Multi-Agent Systems
  Riya Bharathwaj; Akshara Prabhakar; Roshan Ram; Avni Kothari; Sarah Tan; Huan Wang; Silvio Savarese
• [44%] Domain-Adversarial Adaptation from MURA to In-House Radiographs for Improved Adult Elbow Fracture Classification
  M. Bolhassani; W. Furtado; D. Duvall; MJ Negahdar; J. Joshi; S. Contractor; A. Amini
• [44%] Data-Efficient Unlearning-Based Backdoor Detection in Federated Learning
  Dowon Kim; Junhao Cai; Sung Il Choi; Dohun Kim; Juhyun Park; Chengjun Jin; Changhee Joo
• [43%] Context-Shielded Backdoor Attack against Large Vision-Language Models
  Zhifang Zhang; Qiang Huang; Chenpeng Wang; Weitong Chen; Olaf Maennel; Wei Emma Zhang; Lei Feng; Lei Zhang; Miao Xu
• [43%] ATrust: Adaptive Trust Boundary Expansion for Securing LLM Agents
  Xu Zhang; Zhichao Lu
• [42%] Right Tool, Wrong Parameters: Defending LLM Agents Against Parameter Poisoning
  Yao Wang; Zehua Ma; Weiming Zhang; Han Fang
• [42%] Toward a theory of Evaluability
  Kunal Talwar
• [41%] Threat Modeling Intimate Partner Abuse in Agentic Systems
  Natalie Grace Brigham; Eugene Bagdasarian; Franziska Roesner; Tadayoshi Kohno
• [41%] MemHarmBench: Evaluating Cross-Session Prompt Injection in Memory-Persistent AI Agents
  Zhihua Wang; Yunhao Feng; Yifeng Gao; Rui Pan; Baiheng Zhao; Zixing Chen; Xingjun Ma
• [41%] The Pen is Mightier than the Pixel: Natural Textual Unlearnable Example for Large Vision Language Models
  Chenyu Yi; Jiawen Zong; Sami Hormi; Bingquan Shen; Xudong Jiang; Alex Chichung Kot
• [41%] RAD-TFM: Robust and Domain-Adapted Tabular Foundation Models
  Matthew Peroni; Franck Le; Vadim Sheinin
• [41%] MGE: A Membership Guided Data Extraction Attack against Diffusion Models
  Yuchang Mei; Longqiang Wang; Haoyang Jiang; Mingyang Yi; Shaolei Zhang; Keman Huang; Wuqiong Pan; Ju Fan
• [40%] UniGADD: Universal Generator-Agnostic Deepfake Detector
  Bernard Tomczyk; Agil Aghasanli; Plamen Angelov
• [40%] PrivMark: Pixel-Space Steering against Privacy Leakage in Vision-Language Models
  Ruofan Xing; Arman Akbari; Weikai Lin; Yuhao Zhu; Xuan Zhang
• [40%] MUTE: Multi-Level Alignment Uncoupling Against Talking-Head Exploitation for Voice Protection
  Donghyun Kim; Jin Hong; Seungmin Kim; Dain Kim; Junseok Kwon; Daeseon Choi
• [40%] POEM: Output-Relative Block-Sparse Attention for Long-Context Prefilling
  Haoyi Wu; Yunkai Dang; Wanyu Zhang; Lei Wang; Wenbin Li

→ 全リストを見る