Security

VIGIL: Defending LLM Agents Against Tool-Stream Injection via Verify-Before-Commit ACL 2026 VishBox v2: A Multi-Agent System for Adaptive Voice Phishing Simulation ACL 2026 WaTeRFlow: Watermark Temporal Robustness via Flow Consistency CVPR 2026 When Anonymity Breaks: Identifying Models Behind Text-to-Image Leaderboards CVPR 2026 When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents? ACL 2026 When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents ACL 2026 When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models ACL 2026 When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters CVPR 2026 XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts ACL 2026 XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants ACL 2026 XSeg: A Large-scale X-ray Contraband Segmentation Benchmark For Real-World Security Screening CVPR 2026 You Can Have a Second Chance: Unbiased and Multi-bit Watermarking for Diffusion Language Models with Regret-based Remasking ACL 2026 Zero-shot Detection of AI-Generated Image via RAW-RGB Alignment CVPR 2026 Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks AAAI 2025 AHSG: Adversarial Attack on High-level Semantics in Graph Neural Networks ACML 2025 A Likelihood Based Approach for Watermark Detection AISTATS 2025 Audio Deepfake Source Tracing using Multi-Attribute Open-Set Identification and Verification Interspeech 2025 A Watermark for Auto-Regressive Speech Generation Models Interspeech 2025 Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection UAI 2025 Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems Interspeech 2025 Can Watermarked LLMs be Identified by Users via Crafted Prompts? ICLR 2025 CBA: Backdoor Attack on Deep Speech Classification via Audio Compression Interspeech 2025 Codec-Based Deepfake Source Tracing via Neural Audio Codec Taxonomy Interspeech 2025 Collecting, Curating, and Annotating Good Quality Speech deepfake dataset for Famous Figures: Process and Challenges Interspeech 2025 Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Interspeech 2025