Key papers

• Filtering Offensive Content Changes Its Visibility but Not User Behavior: Two Randomized Controlled Trials with 200,000 Users on Nextdoor (2026)
  David J. Gr\"uning et al.
  5.49
• Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data (2026)
  Vin\'icius Gabriel Angelozzi et al.
  5.01
• Plausible Deniability Guarantees for Whistleblowers (2026)
  Leo Richter et al.
  5.01
• Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers Optimization (2026)
  Bingjun Luo et al.
  5.01
• Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks (2026)
  Michael Kouremetis et al.
  5.01
• ToolGuardian: Declarative Security for AI Agent-Tool Interactions (2026)
  Arun Ravindran et al.
  5.01
• Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification (2026)
  Carter Luck et al.
  5.01
• ISPCloak: Weaponizing ISP for Optimization-Free Physical Camouflage against Deepfake Detectors (2026)
  Jiale Zhao et al.
  5.01
• Practical Graph Optimisation and AI-Driven Models for Active Directory Security Hardening (2026)
  Huy Q. Ngo
  5.01
• Agent Security Needs Redefinition through a Holistic Framework (2026)
  Vincent Siu et al.
  5.01
• Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints (2026)
  Alan Gany et al.
  4.39
• Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents (2026)
  Vikas Reddy et al.
  4.39
• Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants (2026)
  Dipesh Tharu Mahato
  4.39
• The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators (2026)
  Dominik Schwarz
  4.39
• SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification (2026)
  SingGuard Team
  4.39
• Securing LLMs in the Wild: Privacy and Security Challenges at the Edge (2026)
  Ren-Yi Huang et al.
  4.39
• SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy (2026)
  Yassine Chemingui et al.
  4.39
• BARS: Benign-Anchored Ranking and Selection for False Alarm Reduction in Network Intrusion Detection (2026)
  Abu Fuad Ahmad et al.
  4.39
• Audited Selective Verification for Risk-Controlled N-1 Thermal Contingency Screening under Deployment Shift (2026)
  Jayakumar Manoharan
  4.39
• Evaluating Frontier AI Agents as Autonomous Clinical Security Auditors (2026)
  Michael O. Eniolade
  4.39
• Adversarial Prompting Framework for AI Safety Assessment (2026)
  Yash Bhatnagar et al.
  4.39
• Explainable Artificial Intelligence for Anomaly Detection in Banking Transactions: An Internal Audit Perspective (2026)
  Anupa Lodhi
  4.39
• When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training (2026)
  Na Li et al.
  4.39
• UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors (2026)
  Dima Galat et al.
  4.39
• Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection (2026)
  Zhenpeng Li
  4.39
• Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation (2026)
  Mohammad Allahbakhsh et al.
  4.39
• Natural Backdoor Attacks on Speech Recognition Models (2026)
  Jinwen Xin et al.
  4.39
• SFGA: A Statistics-First Gating Architecture with Adjudicative Escalation for Trustworthy SFT Data Procurement (2026)
  Arther Tian et al.
  4.39
• ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D (2026)
  Lena Libon et al.
  4.39
• Risk Is Not the Target: A Monotonic Framework for Evaluating Wildfire Operational Risk Signals (2026)
  Nicolas Caron et al.
  4.39
• Securing Multimodal AI through Internal Information Decomposition (2026)
  Jehyeok Yeon et al.
  4.39
• What AI Red-Team Evaluations Can and Cannot Prove (2026)
  Bandana Kaur
  4.39
• Probing Speaker Identity Sensitivity in Audio Deepfake Detectors (2026)
  Daniyal Kabir Dar et al.
  4.39
• DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection (2026)
  Xiafeng Man
  4.39
• Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI (2026)
  Jiaqi Shao et al.
  4.39
• Where Is the Cost of Third-Party API Routers in Agentic Software Development? (2026)
  Donghao Fu et al.
  4.39
• Do Models Fake Alignment Without Clear Consequences? (2026)
  Cole Alexander Niblett et al.
  4.39
• I2VShield: An Efficient Proactive Defense Framework against DiT-based Image-to-Video Models (2026)
  Yimao Guo et al.
  4.39
• GPT-Red: Automated Red Teaming via Self-Play at Scale (2026)
  Eric Wallace et al.
  4.36
• StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents (2026)
  Ads Dawson et al.
  4.36
• Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents (2026)
  Paul Kassianik et al.
  3.51
• Hidden in Thought: Transferable Chain-of-Thought Artifacts Induce Harmful Behavior (2026)
  Ali khalil et al.
  3.51
• Quantum Cryptanalysis on IBM Quantum Hardware: Extending Even--Mansour Period Recovery from $N=4$ to $N=10$ (2026)
  Taebong Kim et al.
  3.51
• Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing (2026)
  Jie Li
  3.51
• Data Leakage Prevention in Agentic Applications via Preemptive Hardening (2026)
  Akansha Shukla et al.
  3.51
• Conspiracy Theory Rabbit Holes Emerge via Interacting Contagions (2026)
  Fabian Tschofenig et al.
  3.51
• Adversarial Prompts for Acceptance Collapse in Speculative Decoding (2026)
  Run Wang et al.
  3.51
• Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control (2026)
  Brett Reynolds
  2.00
• G2VD: Generalizable AI-Generated Video Detection via Counterfactual Intervention and Causal Disentanglement (2026)
  Meng Du et al.
  2.00
• BioSecBench-Refusal: A paired metric for performance and alignment in agentic biosecurity risk assessment (2026)
  Edwin H. Wintermute et al.
  2.00
• Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents (2026)
  Or Zion Eliav et al.
  2.00
• Lilith: Backdoor Generalization under Training-Inference Trigger Shift (2026)
  Zhou Feng et al.
  2.00
• (EC)2: Event-Centric Explainability for Cybersecurity Through Multi-Agent LLM Investigations (2026)
  Neta Kirmayer et al.
  2.00
• Contextualized Counterspeech Can Be More Persuasive Than Generic Counterspeech (2026)
  Lorenzo Cima et al.
  2.00
• SARC-DQ: Runtime Data-Quality Gating for Agentic AI: Silent Evidence Defects, the Incompetence Shield, and Downstream-Only Remediation (2026)
  Gaston Besanson
  2.00
• RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning (2026)
  Pushkal Kumar et al.
  2.00
• Collusion with Competitive Marginals: Price-Level Audits Are Blind by Construction (2026)
  Xin Xu et al.
  2.00
• Recover, Decode, Reguard: Guard-Agnostic Defense Amplification againstEncoded VLM Jailbreaks (2026)
  Haoyu Zhang et al.
  2.00
• Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses (2026)
  Haoyu Zhang et al.
  2.00
• FakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking (2026)
  Mu\~noz-Haro Javier et al.
  2.00