{"total":6415,"rows":[{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104,"area":"alignment"},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"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":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420,"area":"safety"},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114,"area":"diffusion"},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944,"area":null},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802,"area":null},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651,"area":"alignment"},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486,"area":"safety"},{"id":"2205.07460","title":"Diffusion Models for Adversarial Purification","created":"2022-05-16","cited_by_count":476,"area":"diffusion"},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469,"area":"safety"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446,"area":null},{"id":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431,"area":"safety"},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431,"area":"alignment"},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2402.06363","title":"StruQ: Defending Against Prompt Injection with Structured Queries","created":"2024-02-09","cited_by_count":375,"area":"safety"},{"id":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328,"area":"mllm"},{"id":"2101.05930","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","created":"2021-01-15","cited_by_count":324,"area":null},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322,"area":"safety"},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321,"area":"safety"},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315,"area":"alignment"},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2101.02703","title":"Distribution-Free, Risk-Controlling Prediction Sets","created":"2021-01-07","cited_by_count":288,"area":null},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284,"area":"mllm"},{"id":"2102.01356","title":"Recent Advances in Adversarial Training for Adversarial Robustness","created":"2021-02-02","cited_by_count":279,"area":null},{"id":"2307.14539","title":"Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models","created":"2023-07-26","cited_by_count":273,"area":"mllm"},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266,"area":"safety"},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260,"area":null},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260,"area":null},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252,"area":null},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249,"area":null},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249,"area":null},{"id":"2103.15571","title":"Enhancing the Transferability of Adversarial Attacks through Variance Tuning","created":"2021-03-29","cited_by_count":244,"area":null},{"id":"2308.07308","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","created":"2023-08-14","cited_by_count":244,"area":"safety"},{"id":"2104.13733","title":"Gradient-based Adversarial Attacks against Text Transformers","created":"2021-04-15","cited_by_count":234,"area":null},{"id":"2110.09468","title":"Improving Robustness using Generated Data","created":"2021-10-18","cited_by_count":234,"area":null},{"id":"2103.06624","title":"Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification","created":"2021-03-11","cited_by_count":228,"area":null},{"id":"2111.08947","title":"Fast Yet Effective Machine Unlearning","created":"2021-11-17","cited_by_count":217,"area":"safety"},{"id":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211,"area":null},{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210,"area":null},{"id":"2310.11868","title":"To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now","created":"2023-10-18","cited_by_count":210,"area":"diffusion"},{"id":"2410.05451","title":"SecAlign: Defending Against Prompt Injection with Preference Optimization","created":"2024-10-07","cited_by_count":210,"area":"alignment"},{"id":"2103.12828","title":"Learning to Optimize: A Primer and A Benchmark","created":"2021-03-23","cited_by_count":208,"area":null},{"id":"2302.04638","title":"Better Diffusion Models Further Improve Adversarial Training","created":"2023-02-09","cited_by_count":208,"area":"diffusion"},{"id":"2105.07581","title":"Vision Transformers are Robust Learners","created":"2021-05-17","cited_by_count":207,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2103.01946","title":"Fixing Data Augmentation to Improve Adversarial Robustness","created":"2021-03-02","cited_by_count":204,"area":null},{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203,"area":null},{"id":"2111.05328","title":"Data Augmentation Can Improve Robustness","created":"2021-11-09","cited_by_count":194,"area":null},{"id":"2311.17516","title":"MMA-Diffusion: MultiModal Attack on Diffusion Models","created":"2023-11-29","cited_by_count":194,"area":"diffusion"},{"id":"2101.04898","title":"Unlearnable Examples: Making Personal Data Unexploitable","created":"2021-01-13","cited_by_count":193,"area":null},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187,"area":null},{"id":"2309.11751","title":"How Robust is Google's Bard to Adversarial Image Attacks?","created":"2023-09-21","cited_by_count":183,"area":"mllm"},{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178,"area":null},{"id":"2203.12208","title":"Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection","created":"2022-03-23","cited_by_count":173,"area":null},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2202.03104","title":"SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation","created":"2022-02-07","cited_by_count":171,"area":null},{"id":"2405.15234","title":"Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models","created":"2024-05-24","cited_by_count":168,"area":"diffusion"},{"id":"2104.02610","title":"On the Robustness of Vision Transformers to Adversarial Examples","created":"2021-03-31","cited_by_count":167,"area":null},{"id":"2302.04578","title":"Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples","created":"2023-02-09","cited_by_count":167,"area":"diffusion"},{"id":"2110.03735","title":"Adversarial Unlearning of Backdoors via Implicit Hypergradient","created":"2021-10-07","cited_by_count":166,"area":null},{"id":"2302.06588","title":"Raising the Cost of Malicious AI-Powered Image Editing","created":"2023-02-13","cited_by_count":163,"area":"diffusion"},{"id":"2102.00436","title":"Admix: Enhancing the Transferability of Adversarial Attacks","created":"2021-01-31","cited_by_count":156,"area":null},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156,"area":"safety"},{"id":"2110.14051","title":"A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges","created":"2021-10-26","cited_by_count":154,"area":null},{"id":"2202.03423","title":"Backdoor Defense via Decoupling the Training Process","created":"2022-02-05","cited_by_count":153,"area":null},{"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,"area":"mllm"},{"id":"2105.12806","title":"A Universal Law of Robustness via Isoperimetry","created":"2021-05-26","cited_by_count":151,"area":null},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151,"area":null},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151,"area":"safety"},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"area":null},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145,"area":"safety"},{"id":"2206.09391","title":"Towards Adversarial Attack on Vision-Language Pre-training Models","created":"2022-06-19","cited_by_count":144,"area":"mllm"},{"id":"2101.06549","title":"AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles","created":"2021-01-16","cited_by_count":137,"area":null},{"id":"2105.07926","title":"Towards Robust Vision Transformer","created":"2021-05-17","cited_by_count":137,"area":null},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135,"area":null},{"id":"2303.08233","title":"NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions","created":"2023-03-14","cited_by_count":135,"area":null},{"id":"2402.02309","title":"Jailbreaking Attack against Multimodal Large Language Model","created":"2024-02-04","cited_by_count":135,"area":"safety"},{"id":"2106.06041","title":"Adversarial purification with Score-based generative models","created":"2021-06-11","cited_by_count":134,"area":"diffusion"},{"id":"2309.01446","title":"Open Sesame! Universal Black Box Jailbreaking of Large Language Models","created":"2023-09-04","cited_by_count":134,"area":"safety"},{"id":"2105.14368","title":"Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation","created":"2021-05-29","cited_by_count":132,"area":null},{"id":"2205.15466","title":"Data Banzhaf: A Robust Data Valuation Framework for Machine Learning","created":"2022-05-30","cited_by_count":132,"area":null},{"id":"2112.05135","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","created":"2021-12-09","cited_by_count":131,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2104.11315","title":"SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics","created":"2021-04-22","cited_by_count":130,"area":null},{"id":"2112.08304","title":"On the Convergence and Robustness of Adversarial Training","created":"2021-12-15","cited_by_count":130,"area":null},{"id":"2207.05382","title":"Frequency Domain Model Augmentation for Adversarial Attack","created":"2022-07-12","cited_by_count":130,"area":null},{"id":"2411.10414","title":"Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations","created":"2024-11-15","cited_by_count":129,"area":"mllm"},{"id":"2510.09023","title":"The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections","created":"2025-10-10","cited_by_count":129,"area":"safety"},{"id":"2103.01050","title":"Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World","created":"2021-03-01","cited_by_count":127,"area":null},{"id":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127,"area":null},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127,"area":null},{"id":"2303.15433","title":"Anti-DreamBooth: Protecting users from personalized text-to-image synthesis","created":"2023-03-27","cited_by_count":120,"area":"diffusion"},{"id":"2311.17717","title":"Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers","created":"2023-11-29","cited_by_count":120,"area":"diffusion"},{"id":"2402.12336","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","created":"2024-02-19","cited_by_count":120,"area":"mllm"},{"id":"2406.12814","title":"Dissecting Adversarial Robustness of Multimodal LM Agents","created":"2024-06-18","cited_by_count":120,"area":"agents"},{"id":"2106.10807","title":"Adversarial Examples Make Strong Poisons","created":"2021-06-21","cited_by_count":119,"area":null}],"next_cursor":"100"}