AI Safety

FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts EMNLP 2025 Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks ICLR 2025 Feint and Attack: Jailbreaking and Protecting LLMs via Attention Distribution Modeling IJCAI 2025 Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique EMNLP 2025 FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts AAAI 2025 Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning ICCV 2025 Fine-Grained Constraint Generation-Verification for Improved Instruction-Following ACL 2025 Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency ACL 2025 FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain EMNLP 2025 FiRC-NLP at SemEval-2025 Task 3: Exploring Prompting Approaches for Detecting Hallucinations in LLMs SemEval 2025 First Line of Defense: A Robust First Layer Mitigates Adversarial Attacks AAAI 2025 Flat Reward in Policy Parameter Space Implies Robust Reinforcement Learning ICLR 2025 FlipAttack: Jailbreak LLMs via Flipping ICML 2025 FLUE: Streamlined Uncertainty Estimation for Large Language Models AAAI 2025 Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems ICLR 2025 Foot-In-The-Door: A Multi-turn Jailbreak for LLMs EMNLP 2025 Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration ICLR 2025 Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks EMNLP 2025 Forget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearning EMNLP 2025 Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage AAAI 2025 Formal Synthesis of Barrier Certificates Using Fourier Kolmogorov-Arnold Network AAAI 2025 Formal Synthesis of Safe Kolmogorov-Arnold Network Controllers with Barrier Certificates IJCAI 2025 Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation EMNLP 2025 Fostering Epistemic Insights into AI Ethics through a Constructionist Pedagogy: An Interdisciplinary Approach to AI Literacy AAAI 2025 Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements ACL 2025