Security

Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning ICLR 2025 SonarGuard2: Ultrasonic Face Liveness Detection Based on Adaptive Doppler Effect Feature Extraction Interspeech 2025 Source Verification for Speech Deepfakes Interspeech 2025 Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks ICLR 2025 STOPA: A Dataset of Systematic VariaTion Of DeePfake Audio for Open-Set Source Tracing and Attribution Interspeech 2025 TADA: Training-free Attribution and Out-of-Domain Detection of Audio Deepfakes Interspeech 2025 Thai Speech Spoofing Detection Dataset with Variations in Speaking Styles Interspeech 2025 Towards Secure User Authentication for Headphones via In-Ear or In-Earcup Microphones Interspeech 2025 Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models Interspeech 2025 VCapAV: A Video-Caption Based Audio-Visual Deepfake Detection Dataset Interspeech 2025 VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents Interspeech 2025 WAKE: Watermarking Audio with Key Enrichment Interspeech 2025 An LLM can Fool Itself: A Prompt-Based Adversarial Attack ICLR 2024 DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution UAI 2024 General Markov Model for Solving Patrolling Games UAI 2024 Illusory Attacks: Information-theoretic detectability matters in adversarial attacks ICLR 2024 Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images ICLR 2024 Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers CVPR 2024 PKAD: Pretrained Knowledge is All You Need to Detect and Mitigate Textual Backdoor Attacks EMNLP 2024 PubDef: Defending Against Transfer Attacks From Public Models ICLR 2024 Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game ICLR 2024 The data-driven transferable adversarial space ACML 2024 Undetectable Watermarks for Language Models COLT 2024 Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning EMNLP 2024 When Your AI Becomes a Target: AI Security Incidents and Best Practices AAAI 2024