{"total":59,"rows":[{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429,"area":"safety"},{"id":"2402.02207","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","created":"2024-02-03","cited_by_count":167,"area":"safety"},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145,"area":"safety"},{"id":"2402.02309","title":"Jailbreaking Attack against Multimodal Large Language Model","created":"2024-02-04","cited_by_count":135,"area":"safety"},{"id":"2310.07676","title":"Composite Backdoor Attacks Against Large Language Models","created":"2023-10-11","cited_by_count":73,"area":"safety"},{"id":"2403.02817","title":"Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications","created":"2024-03-05","cited_by_count":59,"area":"safety"},{"id":"2406.05113","title":"LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models","created":"2024-06-07","cited_by_count":52,"area":"safety"},{"id":"2405.19103","title":"Voice Jailbreak Attacks Against GPT-4o","created":"2024-05-29","cited_by_count":42,"area":"safety"},{"id":"2405.19360","title":"ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users","created":"2024-05-24","cited_by_count":35,"area":"safety"},{"id":"2404.12916","title":"Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models","created":"2024-04-19","cited_by_count":33,"area":"safety"},{"id":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32,"area":"safety"},{"id":"2405.16567","title":"Automatic Jailbreaking of the Text-to-Image Generative AI Systems","created":"2024-05-26","cited_by_count":23,"area":"safety"},{"id":"2407.11867","title":"Targeted Unlearning with Single Layer Unlearning Gradient","created":"2024-07-16","cited_by_count":18,"area":"safety"},{"id":"2505.14103","title":"AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models","created":"2025-05-20","cited_by_count":18,"area":"safety"},{"id":"2503.16023","title":"BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models","created":"2025-03-20","cited_by_count":17,"area":"safety"},{"id":"2410.03489","title":"Gradient-based Jailbreak Images for Multimodal Fusion Models","created":"2024-10-04","cited_by_count":14,"area":"safety"},{"id":"2412.20392","title":"Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning","created":"2024-12-29","cited_by_count":12,"area":"safety"},{"id":"2409.19734","title":"T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition","created":"2024-09-29","cited_by_count":11,"area":"safety"},{"id":"2404.08793","title":"JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models","created":"2024-04-12","cited_by_count":7,"area":"safety"},{"id":"2603.01228","title":"Towards Policy-Adaptive Image Guardrail: Benchmark and Method","created":"2026-03-01","cited_by_count":6,"area":"safety"},{"id":"2312.14923","title":"Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models","created":"2023-12-22","cited_by_count":5,"area":"safety"},{"id":"2502.00653","title":"Towards Robust Multimodal Large Language Models Against Jailbreak Attacks","created":"2025-02-02","cited_by_count":5,"area":"safety"},{"id":"2505.18864","title":"Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework","created":"2025-05-24","cited_by_count":5,"area":"safety"},{"id":"2510.12119","title":"ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation","created":"2025-10-14","cited_by_count":4,"area":"safety"},{"id":"2510.23960","title":"SafeVision: Efficient Image Guardrail with Robust Policy Adherence and Explainability","created":"2025-10-28","cited_by_count":4,"area":"safety"},{"id":"2502.05772","title":"Effective Black-Box Multi-Faceted Attacks Breach Vision Large Language Model Guardrails","created":"2025-02-09","cited_by_count":3,"area":"safety"},{"id":"2510.17277","title":"PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs","created":"2025-10-20","cited_by_count":3,"area":"safety"},{"id":"2601.05339","title":"Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models","created":"2026-01-08","cited_by_count":3,"area":"safety"},{"id":"2605.05909","title":"Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning","created":"2026-05-07","cited_by_count":3,"area":"safety"},{"id":"2407.03045","title":"JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery from Large-Scale Human-LLM Conversational Datasets","created":"2024-07-03","cited_by_count":2,"area":"safety"},{"id":"2410.19096","title":"Watermarking Large Language Models and the Generated Content: Opportunities and Challenges","created":"2024-10-24","cited_by_count":2,"area":"safety"},{"id":"2505.16643","title":"From Evaluation to Defense: Advancing Safety in Video Large Language Models","created":"2025-05-22","cited_by_count":2,"area":"safety"},{"id":"2505.24232","title":"From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models","created":"2025-05-30","cited_by_count":2,"area":"safety"},{"id":"2507.03281","title":"NOVO: Unlearning-Compliant Vision Transformers","created":"2025-07-04","cited_by_count":2,"area":"safety"},{"id":"2507.20503","title":"Customize Multi-modal RAI Guardrails with Precedent-based predictions","created":"2025-07-28","cited_by_count":2,"area":"safety"},{"id":"2605.04700","title":"Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization","created":"2026-05-06","cited_by_count":2,"area":"safety"},{"id":"2312.03419","title":"Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models","created":"2023-12-06","cited_by_count":1,"area":"safety"},{"id":"2410.08069","title":"Unlearning-based Neural Interpretations","created":"2024-10-10","cited_by_count":1,"area":"safety"},{"id":"2510.01157","title":"Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models","created":"2025-10-01","cited_by_count":1,"area":"safety"},{"id":"2510.01494","title":"Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed","created":"2025-10-01","cited_by_count":1,"area":"safety"},{"id":"2512.01185","title":"DefenSee: Dissecting Threat from Sight and Text -- A Multi-View Defensive Pipeline for Multi-modal Jailbreaks","created":"2025-12-01","cited_by_count":1,"area":"safety"},{"id":"2512.01314","title":"TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidance","created":"2025-12-01","cited_by_count":1,"area":"safety"},{"id":"2403.16151","title":"Ultra Low-Cost Two-Stage Multimodal System for Non-Normative Behavior Detection","created":"2024-03-24","cited_by_count":0,"area":"safety"},{"id":"2506.11253","title":"Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models","created":"2025-06-12","cited_by_count":0,"area":"safety"},{"id":"2509.12724","title":"Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models","created":"2025-09-16","cited_by_count":0,"area":"safety"},{"id":"2510.21214","title":"Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses","created":"2025-10-24","cited_by_count":0,"area":"safety"},{"id":"2602.17088","title":"MeGU: Machine-Guided Unlearning with Target Feature Disentanglement","created":"2026-02-19","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":"2605.07490","title":"Cross-Modal Backdoors in Multimodal Large Language Models","created":"2026-05-08","cited_by_count":0,"area":"safety"},{"id":"2605.10764","title":"Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.17128","title":"New Wide-Net-Casting Jailbreak Attacks Risk Large Models","created":"2026-05-16","cited_by_count":0,"area":"safety"},{"id":"2605.25194","title":"Localize and Neutralize: Gradient-guided Token Suppression against Visual Prompt Injection Attack","created":"2026-05-24","cited_by_count":0,"area":"safety"},{"id":"2607.04339","title":"One Framework for All: Cross-Modal Membership Inference for Generative Models","created":"2026-07-05","cited_by_count":0,"area":"safety"},{"id":"2608.03210","title":"ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization","created":"2026-08-04","cited_by_count":0,"area":"safety"},{"id":"2608.24354","title":"Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs","created":"2026-08-25","cited_by_count":0,"area":"safety"},{"id":"2608.25490","title":"MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities","created":"2026-08-26","cited_by_count":0,"area":"safety"},{"id":"2609.34641","title":"Backdoor as Probe: Test-Time Adversarial Defense for CLIP","created":"2026-09-28","cited_by_count":0,"area":"safety"},{"id":"2609.36121","title":"Render Before Reading: Visual Rendering as a Prompt Injection Defense","created":"2026-09-28","cited_by_count":0,"area":"safety"},{"id":"2610.17332","title":"COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration","created":"2026-10-12","cited_by_count":0,"area":"safety"}],"next_cursor":null}