Key papers

• Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go? (2026)
  Yimeng Chen et al.
  6.49
• What Happens to Accuracy When Photo Lineups Contain Non-Mated Rank-One Images From Large Galleries? (2026)
  Genesis Argueta et al.
  5.49
• Secure-by-Disguise: A Systematic Evaluation of Image Disguising for Confidential Medical Image Modeling (2026)
  Jason Rojas et al.
  5.01
• TopoGuard: Graph Theory Based Defenses Against Split-Knowledge Attacks on RAG (2026)
  Chahana Dahal et al.
  5.01
• Adversarial Prompts for Acceptance Collapse in Speculative Decoding (2026)
  Run Wang et al.
  5.01
• ISPCloak: Weaponizing ISP for Optimization-Free Physical Camouflage against Deepfake Detectors (2026)
  Jiale Zhao et al.
  5.01
• Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents (2026)
  Harry Owiredu-Ashley
  4.39
• SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification (2026)
  SingGuard Team
  4.39
• A Geometry-Limited Identification Floor and Its Consequences for Voice-Clone Attribution in Professional Voice Actors (2026)
  Shuhei Kato
  4.39
• SpeechGuard: Online Defense against Backdoor Attacks on Speech Recognition Models (2026)
  Jinwen Xin et al.
  4.39
• AI Watermark Evidence Fails Forensic Readiness: An Empirical Evaluation (2026)
  Saifur Rahman Tamim et al.
  4.39
• Code Division Modulation Layers Against Forgetting and Inference in Continual Gait Identification (2026)
  Simone Milani
  4.39
• Toward Interpretable Speech Deepfake Detection using Artifact-Specific Experts and Calibrated Detection Scores (2026)
  Viola Negroni et al.
  4.39
• Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration (2026)
  Vishnu Bindu Balachandran
  4.39
• Physiological Signals as a Forensic Modality for Talking-Face Deepfake Detection (2026)
  Othmane Harraq et al.
  4.39
• Abductive Corroboration of Probabilistic AI Models for Forensic Synthetic Media Detection (2026)
  Junade Ali
  3.51
• Unlearnable Faces: Privacy Protection Surviving Extraction Pipeline (2026)
  Byunghoon Oh et al.
  3.51
• RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations (2026)
  Woo Jae Kim et al.
  3.51
• Verification of Dynamic Holographic Behavior in Identity Documents (2026)
  Glen Pouliquen (IDnow Research Center et al.
  3.51
• Data Safety: Synthetic Data Quality Analysis Using CIFAKE Dataset (2026)
  Kuniko Paxton et al.
  3.51
• VanillaBench: The Hidden Accuracy Cost of Adversarial Robustness (2026)
  Niklas Bunzel
  3.51
• How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions (2026)
  Yukai Zhou et al.
  3.51
• An Early Warning of Emerging Biosecurity Risks in Frontier LLMs (2026)
  Zhida He et al.
  3.51
• Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization (2026)
  Igor Maljkovic et al.
  1.83
• When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm (2026)
  Ye Leng et al.
  1.78
• Towards Context-Aware Image Anonymization with Multi-Agent Reasoning (2026)
  Robert Aufschl\"ager et al.
  1.78
• PRISM-XR: Empowering Privacy-Aware XR Collaboration with Multimodal Large Language Models (2026)
  Jiangong Chen et al.
  1.72
• NWaaS: A Non-Intrusive and Privacy-Preserving Watermarking-as-a-Service System with Adaptive Resource Scheduling (2025)
  Haonan An et al.
  1.33
• Robust Multi-modal Face Anti-spoofing With Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-labels, And Model Degradation (2025)
  Ming-Tsung Hsu, Fang-Yu Hsu, Yi-Ting Lin, et al.
  1.28
• Unmasking Synthetic Realities In Generative AI: A Comprehensive Review Of Adversarially Robust Deepfake Detection Systems (2025)
  Naseem Khan, Tuan Nguyen, Amine Bermak, et al.
  1.28