{"total":41,"rows":[{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2405.20978","title":"Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training","created":"2024-05-31","cited_by_count":89,"area":"lr"},{"id":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61,"area":"lr"},{"id":"2411.18275","title":"Visual Adversarial Attack on Vision-Language Models for Autonomous Driving","created":"2024-11-27","cited_by_count":36,"area":"lr"},{"id":"2412.15206","title":"AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving","created":"2024-12-19","cited_by_count":35,"area":"lr"},{"id":"2402.14899","title":"Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image","created":"2024-02-22","cited_by_count":26,"area":"lr"},{"id":"2501.13563","title":"Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving","created":"2025-01-23","cited_by_count":24,"area":"lr"},{"id":"2505.14667","title":"SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment","created":"2025-05-20","cited_by_count":24,"area":"lr"},{"id":"2509.16645","title":"ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents","created":"2025-09-20","cited_by_count":23,"area":"lr"},{"id":"2405.14169","title":"Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography","created":"2024-05-23","cited_by_count":18,"area":"lr"},{"id":"2511.01758","title":"RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks","created":"2025-11-03","cited_by_count":13,"area":"lr"},{"id":"2503.06254","title":"Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation","created":"2025-03-08","cited_by_count":12,"area":"lr"},{"id":"2505.17406","title":"Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning","created":"2025-05-23","cited_by_count":11,"area":"lr"},{"id":"2511.10714","title":"BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":8,"area":"lr"},{"id":"2310.05450","title":"Empower Nested Boolean Logic via Self-Supervised Curriculum Learning","created":"2023-10-09","cited_by_count":7,"area":"lr"},{"id":"2505.23518","title":"TRAP: Targeted Redirecting of Agentic Preferences","created":"2025-05-29","cited_by_count":5,"area":"lr"},{"id":"2603.23117","title":"TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches","created":"2026-03-24","cited_by_count":5,"area":"lr"},{"id":"2211.15593","title":"GPT-Neo for commonsense reasoning -- a theoretical and practical lens","created":"2022-11-28","cited_by_count":4,"area":"lr"},{"id":"2508.05167","title":"PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems","created":"2025-08-07","cited_by_count":4,"area":"lr"},{"id":"2512.23881","title":"Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack","created":"2025-12-29","cited_by_count":4,"area":"lr"},{"id":"2507.00817","title":"CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs","created":"2025-07-01","cited_by_count":3,"area":"lr"},{"id":"2511.22888","title":"Adversarial Training for Process Reward Models","created":"2025-11-28","cited_by_count":3,"area":"lr"},{"id":"2401.04290","title":"StarCraftImage: A Dataset For Prototyping Spatial Reasoning Methods For Multi-Agent Environments","created":"2024-01-09","cited_by_count":2,"area":"lr"},{"id":"2509.21401","title":"JaiLIP: Jailbreaking Vision-Language Models via Loss Guided Image Perturbation","created":"2025-09-24","cited_by_count":2,"area":"lr"},{"id":"2303.13588","title":"Efficient Symbolic Reasoning for Neural-Network Verification","created":"2023-03-23","cited_by_count":1,"area":"lr"},{"id":"2511.22351","title":"INSIGHT: An Interpretable Neural Vision-Language Framework for Reasoning of Generative Artifacts","created":"2025-11-27","cited_by_count":1,"area":"lr"},{"id":"2601.18386","title":"ARMOR: Agentic Reasoning for Methods Orchestration and Reparameterization for Robust Adversarial Attacks","created":"2026-01-26","cited_by_count":1,"area":"lr"},{"id":"2603.12930","title":"Rethinking VLMs for Image Forgery Detection and Localization","created":"2026-03-13","cited_by_count":1,"area":"lr"},{"id":"2605.11636","title":"Seir\\^enes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2609.22228","title":"Assessing Adversarial Robustness of Latent Reasoning Models","created":"2026-09-03","cited_by_count":1,"area":"lr"},{"id":"2501.19143","title":"Imitation Game for Adversarial Disillusion with Chain-of-Thought Reasoning in Generative AI","created":"2025-01-31","cited_by_count":0,"area":"lr"},{"id":"2510.06790","title":"Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness","created":"2025-10-08","cited_by_count":0,"area":"lr"},{"id":"2510.15948","title":"VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Search","created":"2025-10-10","cited_by_count":0,"area":"lr"},{"id":"2511.12155","title":"Rethinking Deep Alignment Through The Lens Of Incomplete Learning","created":"2025-11-15","cited_by_count":0,"area":"lr"},{"id":"2512.04228","title":"Addressing Logical Fallacies In Scientific Reasoning From Large Language Models: Towards a Dual-Inference Training Framework","created":"2025-12-03","cited_by_count":0,"area":"lr"},{"id":"2512.10414","title":"Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention","created":"2025-12-11","cited_by_count":0,"area":"lr"},{"id":"2604.23238","title":"Hiding in Plain Sight: Detectability-Aware Antidistillation of Reasoning Models","created":"2026-04-25","cited_by_count":0,"area":"lr"},{"id":"2604.23413","title":"Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition","created":"2026-04-25","cited_by_count":0,"area":"lr"},{"id":"2607.05541","title":"Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillation","created":"2026-07-06","cited_by_count":0,"area":"lr"},{"id":"2607.17786","title":"Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2609.21363","title":"Hiding in Plain Sight: A Diffusion-based Mitigation of Geolocation Privacy Leakage in Vision-Language Models","created":"2026-09-18","cited_by_count":0,"area":"lr"}],"next_cursor":null}