| 1 | ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender | Qiyao Ma, Xiaodong Liu, Weiwei Yang +9 | cs.CL | 2026-10-29 |
| 2 | Difficulty Calibration Across Time for Membership Inference in Diffusion Models | Michael Joseph, Yedid Hoshen | cs.CV | 2026-10-29 |
| 3 | How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates | Max Neuwinger, Hanna Yukhymenko, Imanol Schlag | cs.CL | 2026-10-29 |
| #4 | Deep Learning Based Behavioral Drift Modeling for Continuous Biometric Authentication | Suprava Saha Dibya, Minar, Abdulla Al Noman +2 | cs.CR | 2026-10-29 |
| #5 | Understanding and Mitigating Role Spoofing in LLMs | Ezra Edelman, Benjamin Edelman, Surbhi Goel +1 | cs.CR | 2026-10-29 |
| #6 | Textual Response-Aware Guidance for Zero-Shot Adversarial Robustness of Vision-Language Models | Yubo Cui, Xianchao Guan, Zheng Zhang | cs.CV | 2026-10-29 |
| #7 | DYNAS: A Dynamic Network Penetration Testing Framework Using Deep Hierarchical Reinforcement Learning | Md. Rakibul Hassan, Majedul Islam, Md. Ashraful Alam +2 | cs.CR | 2026-10-29 |
| #8 | Tokenizer Tokens Tell Training Tales | Nishita Jain, Parth Upman, Shreyank N Gowda | cs.CL | 2026-10-29 |
| #9 | LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models | Alexandros Gkillas, Ioulia Kapsali, Christos Anagnostopoulos +1 | cs.CV | 2026-10-29 |
| #10 | Surprise Alone Learns Lies: Evidence-Gated Continual Learning for LLMs from Streaming Claims | Abdelkader Metales, Miriam Grabenheinrich | cs.LG | 2026-10-29 |
| #11 | Red-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin | Paula Chikaodinaka Anyanwu, Valdini Douglace Lemofouet, Blessing Ngozi Uzor +7 | cs.CL | 2026-10-29 |
| #12 | Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection | Xinyan Wang, Xiaogeng Liu, Jun Shao +1 | cs.CR | 2026-10-29 |
| #13 | Uncertainty-Guided Cross-Modal Alignment for Diffusion-Based IoT Intrusion Detection | Mahdi Arab Loodaricheh, Anita Raja, Mohammad Hossein Manshaei | cs.LG | 2026-10-29 |
| #14 | Lev-3B: A Data Recipe for Compact Probabilistic Log Decision Models | Leo Betthauser, Yingqi Liu, Uday Shah +5 | cs.LG | 2026-10-28 |
| #15 | FlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models | Xiaogeng Liu, Xinyan Wang, Chaowei Xiao | cs.CR | 2026-10-28 |
| #16 | Where You Inject Matters: The Trust Region Effect in LLM Agents | Chengquan Guo, Xiaodong Liu, Weiwei Yang +7 | cs.AI | 2026-10-28 |
| #17 | Trustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and Robustness | Long Dang, Ali Alfatemi, Kaiqi Xiong +4 | cs.CR | 2026-10-28 |
| #18 | Adversarial Self-Distillation | Mohammad Sadegh Akhondzadeh, Soroush H. Zargarbashi, Aleksandar Bojchevski | cs.LG | 2026-10-28 |
| #19 | How Deterministic SAST and AI Security Agents Divide the Work: Coverage, Harness Policy and Cost in Snyk VulnBench 2.0 | Liran Tal, Chris Liu, Charlotte Fereday +2 | cs.CR | 2026-10-28 |
| #20 | Rethinking LLM Jailbreak Evaluation: Continuous Risk Landscapes Beyond Binary Outcomes | Yukai Zhou, Wenjie Wang | cs.LG | 2026-10-28 |
| #21 | Manifest-Assisted Retrieval in Artificial Intelligence Search: Evidence Gaps and a Security Evaluation | Gangzhen Qian, Kainan Zhou, Chuhong Xu +5 | cs.CR | 2026-10-28 |
| #22 | Does 3D Pose Improve Action Valuation in Football? An Empirical Study of Pose Representations and Learning Objectives | Rikuhei Umemoto, Kenjiro Ide, Soham Majumder +2 | cs.CV | 2026-10-28 |
| #23 | Is it my preference? Role Grounding Attack against Agent's Memory via Social Interaction | Haoran Bu, Yiting Shen, Litian Zhang +2 | cs.CR | 2026-10-28 |
| #24 | A Gradient based Adversarial Augmentation Framework for Mitigating Unlearnable Datasets | Long Dang, Satpal Sura, Kaiqi Xiong | cs.LG | 2026-10-28 |
| #25 | A Separation Principle for Adversarial Attacks and Defense of Graph Neural Networks | Farid Mafi, Saber Jafarpour, Mohammad Pirani | cs.LG | 2026-10-28 |
| #26 | Post-Training Large Language Models with LLMON | Basel Shbita, Michael Hind, Chad DeLuca +8 | cs.AI | 2026-10-28 |
| #27 | Jailbreak Connectivity: Towards Diverse, Transferable, and Universal Multimodal Large Language Model Jailbreak | Xu Zhang, Ziqing Hu, Shuo Han +1 | cs.LG | 2026-10-28 |
| #28 | What Can Firms Do in the Face of Model Distillation? | Diptangshu Sen, Jibang Wu, Juba Ziani | cs.GT | 2026-10-28 |
| #29 | Where Can We Fool the Model's Mind? Response-Guided Semantic Probing and Adaptive Routing for Transferable Attacks on Black-Box MLLMs | Ahmed Abdelnaby, Mohamed Elmahallawy | cs.CV | 2026-10-27 |
| #30 | Preserving Safety During Sequential Fine-Tuning: A Factorial and Geometric Analysis of Replay | George Ruellan, Diana Benavides-Prado | cs.LG | 2026-10-27 |
| #31 | Scan Before You Install: Detecting and Mitigating Local and Composite Vulnerabilities in Skills | Parth A. Gandhi, Avital Aviv, Prasanna N. Wudali +2 | cs.CR | 2026-10-27 |
| #32 | Learning Without Clocks: Partition-Invariant Neural Network | Han Wang, Jingyuan Bao, Juntao Wu +2 | cs.LG | 2026-10-27 |
| #33 | Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness | Igor Shilov, Xiaoxue Yang, Alexander Panfilov +6 | cs.LG | 2026-10-27 |
| #34 | Agentic Backdoors via Pretraining Poisoning | Xinyan Hu, Pingbang Hu, Chloe Loughridge +5 | cs.CR | 2026-10-27 |
| #35 | Follow the Gradient: Tracing Safety Degradation Back to Training Data | Saket Reddy, Amro Abbas, Anshuman Suri +3 | cs.LG | 2026-10-27 |
| #36 | Poisoned Skills: Propagating Jailbreaks Through Agent Markdown Files | Kashyap R Manjusha, Murali Emani | cs.CR | 2026-10-27 |
| #37 | When Is a Relation Worth Trusting? Manipulation Costs, Exposure, and the Trust Trap in Multi-Relational Graph Learning | Vincess Dongmo, Astride Melvin Fokam Ninyim | cs.LG | 2026-10-27 |
| #38 | RePAIR: Inverting Backdoor Attacks in Semantic Segmentation | Arnold Brosch, Kira Maag | cs.CV | 2026-10-27 |
| #39 | Forget the Data, Keep the Capability: Switchable Unlearning for Retrieval | Jingong Chen, Kyle Gao, Guangyuan Li +3 | cs.CV | 2026-10-27 |
| #40 | Quantifying and Prioritizing Stealthy Source-Manipulation Threats Against Multi-Source Anomaly Detectors | Indraveni Chebolu, Seema Panghal, Arnab Mallick +1 | cs.CR | 2026-10-27 |
| #41 | When Does Perturbation Consistency Add Information Beyond Softmax Confidence? Theory and Evidence for the Decision Consistency Framework | Amit Kalitaa, Moirangthem Tiken Singh | cs.LG | 2026-10-27 |
| #42 | ARISE: Authentic Reference-Informed Stability Enhancement for Continual Multimodal Forgery Detection | Yuchen Zhang, Yaxiong Wang, Yujiao Wu +6 | cs.CV | 2026-10-27 |
| #43 | A Simple Presentation of Robust Membership Inference Attacks | Renaud Gaucher, Ephraim Linder, Adam Smith +2 | cs.CR | 2026-10-27 |
| #44 | High-Fidelity Aerostructural Dataset of Transonic Wings in Cruise Conditions | Pavankumar Koratikere, Abhijnan Dikshit, Leifur Leifsson | cs.LG | 2026-10-27 |
| #45 | ORBITAL: Optimization of Robust Brain--Computer Inference Through Architecture-Aware Low-Precision Compression | Saim Rehman, Muhammad Shafique | cs.CV | 2026-10-26 |
| #46 | Spiking Neural Networks Are Harder to Steal: A Benchmark Study of Model Stealing Attacks | Ayana Moshruba, Maryam Parsa | cs.AI | 2026-10-26 |
| #47 | Detecting and Mitigating Query-Based System Prompt Leakage Attacks | Tushar Nayan, Pratik Poudel, Qian Lou +3 | cs.CR | 2026-10-26 |
| #48 | Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol | Yuepeng Hu, Chongyu Fan, Sirat Samyoun +1 | cs.CR | 2026-10-26 |
| #49 | SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy | Mingqian Feng, Xiaodong Liu, Weiwei Yang +7 | cs.CL | 2026-10-26 |
| #50 | Printed and Scanned: Exposing the Fragility of Single-Image Morphing Attack Detectors under Print-Scan Degradation | Diogo J. Paulo, Hugo Proença, João C. Neves | cs.CV | 2026-10-26 |