Key papers

• HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment (2026)
  Shei Pern Chua et al.
  7.37
• Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring (2026)
  William Hackett 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
• Analyzing Toxic Behavior and Its Impact on the Mastodon Community (2026)
  Pasan Kamburugamuwa et al.
  5.01
• Practical Graph Optimisation and AI-Driven Models for Active Directory Security Hardening (2026)
  Huy Q. Ngo
  5.01
• Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software (2026)
  Arastoo Zibaeirad et al.
  4.95
• When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents (2026)
  George Torres et al.
  4.39
• Detecting Neural Network Failures through Spectral Analysis of Internal Activations (2026)
  Arunan J
  4.39
• Exposing the Illusion of Erasure in Knowledge Editing for LLMs (2026)
  Advik Raj Basani et al.
  4.33
• What Does It Mean to Break a Distillation Defense? (2026)
  Lena Libon et al.
  4.33
• Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings (2026)
  Jonas Sch\"afer et al.
  4.33
• CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking (2026)
  Joeun Kim et al.
  3.45
• Format-Controlled Multi-Scale JPEG Compression Response Analysis for Image-Level Forgery Screening (2026)
  Sujith K Mandala
  2.00
• From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents (2026)
  Yiqi Wang et al.
  1.94
• Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs (2026)
  Md Abdullah Al Mamun et al.
  1.94
• Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems (2026)
  Sajjad Khan
  1.94
• Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go? (2026)
  Yimeng Chen et al.
  1.94
• AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection (2026)
  Zijie Zhao et al.
  1.83
• AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems (2026)
  Yihao Zhang et al.
  1.78
• From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection (2025)
  Chaomeng Lu et al.
  1.61
• Security Without Detection: Economic Denial as a Primitive for Edge and IoT Defense (2025)
  Samaresh Kumar Singh et al.
  1.61
• MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts? (2025)
  Muntasir Wahed et al.
  1.33
• Smoothed Embeddings for Robust Language Models (2025)
  Ryo Hase et al.
  1.00
• Robust LLM safeguarding via refusal feature adversarial training (2024)
  Lei Yu et al.
  —
• Exposing LLM Vulnerabilities: Adversarial Scam Detection and Performance (2024)
  Chen-Wei Chang et al.
  —