{"total":15,"rows":[{"id":"2410.02163","title":"Adversarial Decoding: Generating Readable Documents for Adversarial Objectives","created":"2024-10-03","cited_by_count":16,"area":"safety"},{"id":"2408.11851","title":"SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming","created":"2024-08-14","cited_by_count":10,"area":"safety"},{"id":"2501.00055","title":"LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models","created":"2024-12-28","cited_by_count":7,"area":"safety"},{"id":"2505.07610","title":"Concept-Level Explainability for Auditing & Steering LLM Responses","created":"2025-05-12","cited_by_count":6,"area":"safety"},{"id":"2604.15022","title":"Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization","created":"2026-04-16","cited_by_count":5,"area":"safety"},{"id":"2601.04740","title":"StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation","created":"2026-01-08","cited_by_count":4,"area":"safety"},{"id":"2607.13075","title":"The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators","created":"2026-07-12","cited_by_count":2,"area":"safety"},{"id":"2511.06212","title":"RAG-targeted Adversarial Attack on LLM-based Threat Detection and Mitigation Framework","created":"2025-11-09","cited_by_count":0,"area":"safety"},{"id":"2601.15331","title":"RECAP: A Resource-Efficient Method for Adversarial Prompting in Large Language Models","created":"2026-01-20","cited_by_count":0,"area":"safety"},{"id":"2604.17020","title":"Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation","created":"2026-04-18","cited_by_count":0,"area":"safety"},{"id":"2605.00699","title":"STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack","created":"2026-05-01","cited_by_count":0,"area":"safety"},{"id":"2605.11612","title":"When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"safety"},{"id":"2606.05787","title":"SentinelRAG: Synthetic Sentinel Knowledge for RAG Database Copyright Protection","created":"2026-06-04","cited_by_count":0,"area":"safety"},{"id":"2607.02072","title":"kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail","created":"2026-07-02","cited_by_count":0,"area":"safety"},{"id":"2609.22981","title":"Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach","created":"2026-09-19","cited_by_count":0,"area":"safety"}],"next_cursor":null}