model vulnerability

Attacker’s Noise Can Manipulate Your Audio-based LLM in the Real World EACL 2026 Imprint of the Forgotten: Stealthy Membership Inference in Unlearned Graph Neural Networks AAAI 2026 Red Teaming Large Reasoning Models ACL 2026 Membership Inference Attacks with False Discovery Rate Control ICCV 2025 SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection EMNLP 2025 SAM Encoder Breach by Adversarial Simplicial Complex Triggers Downstream Model Failures ICCV 2025 Superfluous Instruction: Vulnerabilities Stemming from Task-Specific Superficial Expressions in Instruction Templates ACL 2025 Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs EMNLP 2025 Why Safeguarded Ships Run Aground? Aligned Large Language Models’ Safety Mechanisms Tend to Be Anchored in The Template Region ACL 2025 FLIRT: Feedback Loop In-context Red Teaming EMNLP 2024 How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities NAACL 2024 Learning the Legibility of Visual Text Perturbations EACL 2023 Unveiling Safety Vulnerabilities of Large Language Models EMNLP 2023 Exploring the Universal Vulnerability of Prompt-based Learning Paradigm NAACL 2022 Membership Inference Attacks Against Self-supervised Speech Models Interspeech 2022 Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems ICML 2022 Evaluating the Vulnerability of End-to-End Automatic Speech Recognition Models to Membership Inference Attacks Interspeech 2021 Adversarial Semantic Collisions EMNLP 2020 Boosting the Transferability of Adversarial Samples via Attention CVPR 2020 advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns ICCV 2019