Key papers

• Embedding Inference Attack (2026)
  Cedric Fitiavana Raelijohn et al.
  5.01
• Black-Box Inference of LLM Architectural Properties with Restrictive API Access (2026)
  Christopher Ellis et al.
  4.39
• Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor (2026)
  Qi Zhao et al.
  4.39
• DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail (2026)
  He Liu et al.
  4.39
• Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety (2026)
  Chigozirim Ifebi et al.
  4.39
• ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm (2026)
  Kefan Song et al.
  4.39
• PromptGraph: Graph-Guided Prompt Sanitization for Balancing Privacy and Utility in LLM Inference (2026)
  Chen Gu et al.
  4.39
• AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation (2026)
  Chenyang Li et al.
  4.39
• Technical Report on the CVPR 2026@AdvML Workshop Challenge (2026)
  Tianyuan Zhang 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
• Adversarial Robustness of Phishing Email Detection: A Comparative Study of TF-IDF + Logistic Regression and Fine-Tuned DistilBERT (2026)
  Tanveer Ahmed et al.
  3.51
• CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization (2026)
  Xinting Liao et al.
  3.51
• Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents (2026)
  Behzad Ousat et al.
  3.51
• Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA (2026)
  Shaswata Mitra et al.
  3.51
• They'll Verify. They Just Won't Act. How Authority Framing and Laundered Code Turn a Trusted Agentic CI/CD Pipeline Into an Attack Surface (2026)
  Yohann Sidot
  3.51
• Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data (2026)
  Vin\'icius Gabriel Angelozzi et al.
  2.00
• Idiobionics: The Unification of Privacy and Intelligent Robotic Prostheses (2026)
  Kwesi Afari Darfoor et al.
  2.00
• Reverse Engineering Compliance: A Dual-Graph Verification Framework for Auditing Legacy IT Security Concepts (2026)
  Lea Roxanne Muth et al.
  2.00
• Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks (2026)
  Junrui Zhang et al.
  2.00
• Untrusted Authors, Trusted Answers: A Calculus of Fidelity-Graded Translations (2026)
  Christoph Kirsch
  2.00
• Verification Without Distrust: Reframing User-Side Oversight as Routine Epistemic Governance in Everyday Human-Chatbot Interaction (2026)
  Aung Pyae
  2.00
• LLM Scheming Inversely Scales with Pretraining Language Coverage (2026)
  Nathan Truong et al.
  2.00
• Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture (2026)
  Anand Gupta et al.
  2.00
• Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenders (2026)
  Ge Zhang et al.
  2.00
• Latent Stability Analysis of Malware Representations Under Feature-Space Perturbations (2026)
  Bamidele Ajayi et al.
  2.00
• MOSAIC-FL, a micro-service based privacy-preserving framework with application to genomics (2026)
  Paul Largillier et al.
  2.00
• SecDrift: Measuring Sector-Conditioned Security Drift in AI-Generated Code (2026)
  Narayanaswami Natraj Bharadwaj et al.
  2.00
• Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks (2026)
  Yu Yan et al.
  2.00
• Hybrid Analysis for Secure MCP Tool Use in LLM Agents (2026)
  Ping He et al.
  2.00
• Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales (2026)
  Genliang Zhu (Accentrust et al.
  2.00
• Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response (2026)
  Abu Bakar Siddik
  2.00
• The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play (2026)
  Michael Macaulay et al.
  2.00
• Bits and Memories: Measuring Verbatim Extraction Across LLM Quantization (2026)
  Akshay Sasi
  2.00
• Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering (2026)
  Maria Rosaria Briglia et al.
  2.00
• Anti-Backdoor Coreset Selection via Cumulative Entropy (2026)
  Qi Zhao et al.
  2.00
• Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models (2026)
  Yongyi Cui et al.
  2.00
• Distributing Security Controls Through Harness Engineering (2026)
  William Robert Gore
  2.00
• From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World (2026)
  Pedro Conde et al.
  1.89
• PEANUT: Perturbations by Eigenvector Alignment for Attacking Graph Neural Networks Under Topology-Driven Message Passing (2026)
  Bhavya Kohli et al.
  1.78
• Robustness Certificates for Neural Networks Against Data Poisoning and Evasion Attacks (2025)
  Sara Taheri et al.
  1.61
• Dataset Poisoning Attacks on Behavioral Cloning Policies (2025)
  Akansha Kalra et al.
  1.56