{"list":"other","total":116,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"1807.03888","title":"A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks","created":"2018-07-10","cited_by_count":1485},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"1812.04606","title":"Deep Anomaly Detection with Outlier Exposure","created":"2018-12-11","cited_by_count":942},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2204.06507","title":"Out-of-Distribution Detection with Deep Nearest Neighbors","created":"2022-04-13","cited_by_count":600},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"1906.02845","title":"Likelihood Ratios for Out-of-Distribution Detection","created":"2019-06-07","cited_by_count":453},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431},{"id":"2311.05608","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","created":"2023-11-09","cited_by_count":398},{"id":"2404.01833","title":"Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack","created":"2024-04-02","cited_by_count":390},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359},{"id":"2110.00218","title":"On the Importance of Gradients for Detecting Distributional Shifts in the Wild","created":"2021-10-01","cited_by_count":339},{"id":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328},{"id":"2202.01197","title":"VOS: Learning What You Don't Know by Virtual Outlier Synthesis","created":"2022-02-02","cited_by_count":300},{"id":"2307.14539","title":"Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models","created":"2023-07-26","cited_by_count":273},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2103.12051","title":"SSD: A Unified Framework for Self-Supervised Outlier Detection","created":"2021-03-22","cited_by_count":264},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261},{"id":"2012.15828","title":"MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers","created":"2020-12-31","cited_by_count":245},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231},{"id":"2404.03027","title":"JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks","created":"2024-04-03","cited_by_count":230},{"id":"2006.08545","title":"Why Normalizing Flows Fail to Detect Out-of-Distribution Data","created":"2020-06-15","cited_by_count":221},{"id":"2211.13445","title":"Delving into Out-of-Distribution Detection with Vision-Language Representations","created":"2022-11-24","cited_by_count":216},{"id":"2402.11753","title":"ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs","created":"2024-02-19","cited_by_count":216},{"id":"2311.03348","title":"Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation","created":"2023-11-06","cited_by_count":214},{"id":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156},{"id":"2402.08567","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","created":"2024-02-13","cited_by_count":153},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2411.16724","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","created":"2024-11-23","cited_by_count":143},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134},{"id":"2501.09004","title":"Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails","created":"2025-01-15","cited_by_count":132},{"id":"2411.10414","title":"Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations","created":"2024-11-15","cited_by_count":129},{"id":"2403.09513","title":"AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting","created":"2024-03-14","cited_by_count":125},{"id":"2307.10490","title":"Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs","created":"2023-07-19","cited_by_count":124},{"id":"2401.02906","title":"MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance","created":"2024-01-05","cited_by_count":117},{"id":"2405.15589","title":"Efficient Adversarial Training in LLMs with Continuous Attacks","created":"2024-05-24","cited_by_count":113},{"id":"2210.10683","title":"Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP","created":"2022-10-19","cited_by_count":102},{"id":"2406.05644","title":"How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States","created":"2024-06-09","cited_by_count":98},{"id":"2402.13494","title":"GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis","created":"2024-02-21","cited_by_count":96},{"id":"2410.10700","title":"LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts","created":"2024-10-14","cited_by_count":86},{"id":"2401.11880","title":"PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety","created":"2024-01-22","cited_by_count":80},{"id":"2405.18166","title":"Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing","created":"2024-05-28","cited_by_count":79},{"id":"1812.02765","title":"Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distance","created":"2018-12-06","cited_by_count":74},{"id":"2406.01288","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","created":"2024-06-03","cited_by_count":70},{"id":"2402.06255","title":"Fight Back Against Jailbreaking via Prompt Adversarial Tuning","created":"2024-02-09","cited_by_count":67},{"id":"2404.12038","title":"Uncovering Safety Risks of Large Language Models through Concept Activation Vector","created":"2024-04-18","cited_by_count":67},{"id":"2502.14881","title":"A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations","created":"2025-02-14","cited_by_count":67},{"id":"2502.03628","title":"The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering","created":"2025-02-05","cited_by_count":66},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64},{"id":"2406.10794","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","created":"2024-06-16","cited_by_count":64},{"id":"2406.05498","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","created":"2024-06-08","cited_by_count":63},{"id":"2412.00473","title":"Jailbreak Large Vision-Language Models Through Multi-Modal Linkage","created":"2024-11-30","cited_by_count":62},{"id":"2203.02194","title":"Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection","created":"2022-03-04","cited_by_count":59},{"id":"2410.15778","title":"Reducing Hallucinations in Vision-Language Models via Latent Space Steering","created":"2024-10-21","cited_by_count":59},{"id":"2406.05113","title":"LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models","created":"2024-06-07","cited_by_count":52},{"id":"2312.10766","title":"JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks","created":"2023-12-17","cited_by_count":50},{"id":"2401.06824","title":"Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective","created":"2024-01-12","cited_by_count":48},{"id":"2503.20823","title":"Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy","created":"2025-03-26","cited_by_count":44},{"id":"2402.00626","title":"Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks","created":"2024-02-01","cited_by_count":38},{"id":"2505.20065","title":"SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety","created":"2025-05-26","cited_by_count":37},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34},{"id":"2502.14744","title":"HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States","created":"2025-02-20","cited_by_count":33},{"id":"2409.11365","title":"CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration","created":"2024-09-17","cited_by_count":31},{"id":"2503.17682","title":"Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback","created":"2025-03-22","cited_by_count":30},{"id":"2405.20653","title":"Mind the Inconspicuous: Revealing the Hidden Weakness in Aligned LLMs' Refusal Boundaries","created":"2024-05-31","cited_by_count":28},{"id":"2506.17209","title":"Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency","created":"2025-06-20","cited_by_count":27},{"id":"2406.06622","title":"Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs","created":"2024-06-07","cited_by_count":26},{"id":"2507.04250","title":"Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning","created":"2025-07-06","cited_by_count":24},{"id":"2409.03788","title":"HSF: Defending against Jailbreak Attacks with Hidden State Filtering","created":"2024-08-31","cited_by_count":23},{"id":"2411.11114","title":"JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit","created":"2024-11-17","cited_by_count":22},{"id":"2411.19187","title":"Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs","created":"2024-11-28","cited_by_count":22},{"id":"2506.09996","title":"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring","created":"2025-06-11","cited_by_count":22},{"id":"2509.03888","title":"False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize","created":"2025-09-04","cited_by_count":19},{"id":"2410.00296","title":"VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild","created":"2024-10-01","cited_by_count":18},{"id":"2404.12274","title":"Advancing the Robustness of Large Language Models through Self-Denoised Smoothing","created":"2024-04-18","cited_by_count":16},{"id":"2505.18588","title":"Safety Alignment via Constrained Knowledge Unlearning","created":"2025-05-24","cited_by_count":14},{"id":"2507.01831","title":"Out-of-Distribution Detection Methods Answer the Wrong Questions","created":"2025-07-02","cited_by_count":14},{"id":"2512.07761","title":"TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards","created":"2025-12-08","cited_by_count":14},{"id":"2506.12707","title":"SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression","created":"2025-06-15","cited_by_count":13}],"next_cursor":"100"}