Key papers

• MusicMark: A Robust Generative Watermarking Framework for Music Generation (2026)
  Seohwan Yun et al.
  5.88
• Manufactured Divisiveness: Decomposing the Hostile Content of Seven Social Media Influence Operations (2026)
  Emilio Ferrara
  5.49
• HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety (2026)
  Navaneeth Sangameswaran et al.
  5.01
• Reverse Engineering Compliance: A Dual-Graph Verification Framework for Auditing Legacy IT Security Concepts (2026)
  Lea Roxanne Muth et al.
  5.01
• TopoGuard: Graph Theory Based Defenses Against Split-Knowledge Attacks on RAG (2026)
  Chahana Dahal et al.
  5.01
• ShriNep@EEUCA 2026: RAKSHAK - Multi-Task DeBERTa with Rationale Distillation and Jigsaw-Augmented Training for Toxic Intent Classification (2026)
  Binayak Karki et al.
  5.01
• Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing (2026)
  Sadegh Majidi et al.
  5.01
• Adversarial Prompts for Acceptance Collapse in Speculative Decoding (2026)
  Run Wang 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
• Efficient Online LLM Watermark Detection via Rao-Blackwellized E-Processes (2026)
  Lu Luo et al.
  5.01
• Analyzing Toxic Behavior and Its Impact on the Mastodon Community (2026)
  Pasan Kamburugamuwa et al.
  5.01
• Analysing Self-Harm Representations in Language Models: a Cross-Architecture Study (2026)
  Luis Espinosa-Anke et al.
  5.01
• Practical Graph Optimisation and AI-Driven Models for Active Directory Security Hardening (2026)
  Huy Q. Ngo
  5.01
• DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection (2026)
  Xiafeng Man
  5.01
• Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences (2026)
  Mark Russinovich et al.
  4.39
• Advanced Topic Modeling Techniques for Categorizing Software Vulnerabilities (2026)
  Utkarsh Tiwari et al.
  4.39
• Piercing Gilbreath's Conjecture: From Deep Number Theory Insights to Fintech and Cybersecurity (2026)
  Vincent Granville
  4.39
• Selective Disclosure Watermarking for Large Language Models (2026)
  Xuyang Chen et al.
  4.39
• Deployment Risk Assessment Using Diff-Aware Features: A Case Study at Prime Video (2026)
  Mayur Kurup et al.
  4.39
• Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies (2026)
  Kiarash Ahi et al.
  4.39
• Quantum-Inspired Contextual Learning for Sparse-Ring Fraud Detection in Dynamic Transaction Graphs (2026)
  Behnam Tonekaboni et al.
  4.39
• PromptGraph: Graph-Guided Prompt Sanitization for Balancing Privacy and Utility in LLM Inference (2026)
  Chen Gu et al.
  4.39
• Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks (2026)
  Santhosh Parampottupadam et al.
  4.39
• Financial Audit Assistance using Misinformation Detection and Explanation (2026)
  Kshitij Madhav Jadhav et al.
  4.39
• Position: AI/ML Deepfake Research is Misaligned with AI-Generated Non-Consensual Intimate Imagery (AIG-NCII) (2026)
  Li Qiwei et al.
  4.39
• Enabling Multilingual Privacy Policy Audits: Large-Scale Analysis of Spanish Mobile Apps (2026)
  Marcos Moran et al.
  4.39
• Hybrid Latent-Structural Fusion (HLSF) for Cyber Anomaly Detection (2026)
  Dorianis M. Perez et al.
  4.39
• Code Division Modulation Layers Against Forgetting and Inference in Continual Gait Identification (2026)
  Simone Milani
  4.39
• FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense (2026)
  Chenyu Zhou et al.
  4.39
• Securing Multimodal AI through Internal Information Decomposition (2026)
  Jehyeok Yeon et al.
  4.39
• MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion (2026)
  Tasfia Nuzhat Ornee et al.
  4.39
• Implement Kubernetes Pod-Level Remote Attestation for Confidential Workloads on dstack (2026)
  Yang Yang et al.
  4.33
• Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing Human (2026)
  Emre Turan
  4.33
• ESLD (External Surrogate Latent Defense): A Latent-Space Architecture for Faster, Stronger Prompt-Injection Defense (2026)
  Yash Narendra
  4.27
• Agent Security is a Systems Problem (2026)
  Mihai Christodorescu et al.
  4.27
• Toward User Comprehension Supports for LLM Agent Skill Specifications (2026)
  Zikai Alex Wen
  4.27
• MRMMIA: Membership Inference Attacks on Memory in Chat Agents (2026)
  Kai Chen et al.
  4.27
• The Surface You Test Is Not the Surface That Breaks (2026)
  Shifat E Arman et al.
  4.27
• RedAgent: An Autonomous Agent for Context-Aware Red Teaming of LLM Jailbreaks (2026)
  Huiyu Xu et al.
  4.20
• Incalmo: An Autonomous Llm-assisted System For Red Teaming Multi-host Networks (2025)
  Brian Singer, Keane Lucas, Lakshmi Adiga, et al.
  3.53
• FLINT: Fingerprinting Federated Learning Architectures from 5G PHY-Layer Side Channels (2026)
  Md Nahid Hasan Shuvo et al.
  3.51
• Boundary-Seeking GAN-Augmented TabTransformer for Adversarially Robust Intrusion Detection (2026)
  Raihan Sultan Pasha Basuki et al.
  3.51
• Fenced Citation-Context Retrieval for Case Law: Temporal Leakage and Degree Control Across Two Jurisdictions (2026)
  Yao Liu et al.
  3.51
• DecoyFace: Beyond Obfuscation via Controllable and Imperceptible Identity Misdirection for Privacy-Preserving Face Recognition (2026)
  Zhihan Ren et al.
  3.51
• Semantic Color Naturalness Breaker: Preventing Illegitimate Colorization via Content-Aware Color Priors (2026)
  Yuki Nii et al.
  3.51
• ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration (2026)
  Chengheng Li-Chen et al.
  3.51
• Using Fine-Tuned LLMs to Identify Indicators of Vulnerability in UK Police Incident Logs (2026)
  Sam Relins et al.
  3.51
• A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems (2026)
  Seyed Bagher Hashemi Natanzi et al.
  3.45
• LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection (2026)
  Lei Zhao et al.
  3.39
• IUU+DB: Tracking Illegal, Unreported, and Unregulated Fishing, Seafood Fraud, and Labor Abuse through LLM-driven Information Extraction (2026)
  Henry Bodwell et al.
  1.94
• The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs (2026)
  Shivam Ratnakar et al.
  1.94
• From Beats to Breaches:How Offensive AI Infers Sensitive User Information from Playlists (2026)
  Stefano Cecconello et al.
  1.89
• Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry (2026)
  Shoumik Saha et al.
  1.89
• XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles (2026)
  Iakovos-Christos Zarkadis et al.
  1.89
• SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors (2026)
  Elle Najt et al.
  1.89
• PrivScope: Task-scoped Disclosure Control for Hybrid Agentic Systems (2026)
  Shafizur Rahman Seeam (Ian) et al.
  1.89
• ADR: An Agentic Detection System for Enterprise Agentic AI Security (2026)
  Chenning Li et al.
  1.89
• FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection (2026)
  Huanchi Wang et al.
  1.89
• Towards Predicting Multi-Vulnerability Attack Chains in Software Supply Chains from Software Bill of Materials Graphs (2026)
  Laura Baird et al.
  1.83