{"total":555,"rows":[{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651,"area":"alignment"},{"id":"2404.01318","title":"JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models","created":"2024-03-28","cited_by_count":536,"area":"safety"},{"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":"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":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266,"area":"safety"},{"id":"2110.09468","title":"Improving Robustness using Generated Data","created":"2021-10-18","cited_by_count":234,"area":null},{"id":"2302.04638","title":"Better Diffusion Models Further Improve Adversarial Training","created":"2023-02-09","cited_by_count":208,"area":"diffusion"},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194,"area":"safety"},{"id":"2310.01469","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","created":"2023-10-02","cited_by_count":177,"area":null},{"id":"2104.02610","title":"On the Robustness of Vision Transformers to Adversarial Examples","created":"2021-03-31","cited_by_count":167,"area":null},{"id":"2405.15556","title":"Certifiably Robust RAG against Retrieval Corruption","created":"2024-05-24","cited_by_count":151,"area":"rag"},{"id":"2406.13352","title":"AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","created":"2024-06-19","cited_by_count":145,"area":"agents"},{"id":"2106.06041","title":"Adversarial purification with Score-based generative models","created":"2021-06-11","cited_by_count":134,"area":"diffusion"},{"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":"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":"2503.00061","title":"Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents","created":"2025-02-27","cited_by_count":125,"area":"agents"},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123,"area":"safety"},{"id":"2104.09425","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","created":"2021-04-19","cited_by_count":113,"area":null},{"id":"2402.09154","title":"Attacking Large Language Models with Projected Gradient Descent","created":"2024-02-14","cited_by_count":94,"area":"alignment"},{"id":"2302.14301","title":"A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking","created":"2023-02-28","cited_by_count":85,"area":null},{"id":"2111.10752","title":"Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability","created":"2021-11-21","cited_by_count":84,"area":null},{"id":"2305.15241","title":"Robust Classification via a Single Diffusion Model","created":"2023-05-24","cited_by_count":79,"area":"diffusion"},{"id":"2103.08307","title":"Improving Adversarial Robustness via Channel-wise Activation Suppressing","created":"2021-03-11","cited_by_count":76,"area":null},{"id":"2206.08451","title":"I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences","created":"2022-06-16","cited_by_count":75,"area":null},{"id":"2110.03825","title":"Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks","created":"2021-10-07","cited_by_count":74,"area":null},{"id":"2403.00867","title":"Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes","created":"2024-03-01","cited_by_count":74,"area":"safety"},{"id":"2411.13587","title":"Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics","created":"2024-11-18","cited_by_count":73,"area":"vla"},{"id":"2209.02128","title":"Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples","created":"2022-09-05","cited_by_count":69,"area":null},{"id":"2108.09135","title":"PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier","created":"2021-08-20","cited_by_count":65,"area":null},{"id":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65,"area":"safety"},{"id":"2202.13711","title":"Evaluating the Adversarial Robustness of Adaptive Test-time Defenses","created":"2022-02-28","cited_by_count":64,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2210.04871","title":"Certified Training: Small Boxes are All You Need","created":"2022-10-10","cited_by_count":52,"area":null},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52,"area":null},{"id":"2102.12827","title":"Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints","created":"2021-02-25","cited_by_count":50,"area":null},{"id":"2108.02488","title":"Poison Ink: Robust and Invisible Backdoor Attack","created":"2021-08-05","cited_by_count":50,"area":null},{"id":"2111.09277","title":"SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness","created":"2021-11-17","cited_by_count":49,"area":null},{"id":"2112.11668","title":"How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?","created":"2021-12-22","cited_by_count":49,"area":null},{"id":"2310.19737","title":"Adversarial Attacks and Defenses in Large Language Models: Old and New Threats","created":"2023-10-30","cited_by_count":49,"area":null},{"id":"2107.11630","title":"Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them","created":"2021-07-24","cited_by_count":48,"area":null},{"id":"2403.01849","title":"One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models","created":"2024-03-04","cited_by_count":48,"area":"mllm"},{"id":"2411.16721","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","created":"2024-11-23","cited_by_count":48,"area":"mllm"},{"id":"2103.14222","title":"Adversarial Attacks are Reversible with Natural Supervision","created":"2021-03-26","cited_by_count":47,"area":null},{"id":"2104.11470","title":"Random Noise Defense Against Query-Based Black-Box Attacks","created":"2021-04-23","cited_by_count":47,"area":null},{"id":"2106.06946","title":"Boosting Randomized Smoothing with Variance Reduced Classifiers","created":"2021-06-13","cited_by_count":47,"area":null},{"id":"2106.14851","title":"Data Poisoning Won't Save You From Facial Recognition","created":"2021-06-28","cited_by_count":45,"area":"safety"},{"id":"2110.07719","title":"Certified Patch Robustness via Smoothed Vision Transformers","created":"2021-10-11","cited_by_count":45,"area":null},{"id":"2203.05154","title":"Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack","created":"2022-03-10","cited_by_count":44,"area":null},{"id":"2203.08519","title":"Towards Practical Certifiable Patch Defense with Vision Transformer","created":"2022-03-16","cited_by_count":44,"area":null},{"id":"2311.11261","title":"Adversarial Prompt Tuning for Vision-Language Models","created":"2023-11-19","cited_by_count":44,"area":"mllm"},{"id":"2405.20446","title":"Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation","created":"2024-05-30","cited_by_count":44,"area":"rag"},{"id":"2102.05363","title":"Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons","created":"2021-02-10","cited_by_count":40,"area":null},{"id":"2103.03344","title":"WaveGuard: Understanding and Mitigating Audio Adversarial Examples","created":"2021-03-04","cited_by_count":40,"area":null},{"id":"2107.10873","title":"On the Certified Robustness for Ensemble Models and Beyond","created":"2021-07-22","cited_by_count":40,"area":null},{"id":"2203.14195","title":"How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective","created":"2022-03-27","cited_by_count":39,"area":null},{"id":"2301.13838","title":"Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression","created":"2023-01-31","cited_by_count":39,"area":null},{"id":"2104.00671","title":"TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness","created":"2021-04-01","cited_by_count":38,"area":null},{"id":"2301.13694","title":"Are Defenses for Graph Neural Networks Robust?","created":"2023-01-31","cited_by_count":38,"area":null},{"id":"2410.13821","title":"Artificial Kuramoto Oscillatory Neurons","created":"2024-10-17","cited_by_count":38,"area":null},{"id":"2106.06196","title":"CausalAdv: Adversarial Robustness through the Lens of Causality","created":"2021-06-11","cited_by_count":37,"area":null},{"id":"2405.20099","title":"Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks","created":"2024-05-30","cited_by_count":37,"area":"safety"},{"id":"2110.13864","title":"FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective","created":"2021-10-26","cited_by_count":36,"area":null},{"id":"2111.09999","title":"TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems","created":"2021-11-19","cited_by_count":36,"area":null},{"id":"2202.13437","title":"A Unified Wasserstein Distributional Robustness Framework for Adversarial Training","created":"2022-02-27","cited_by_count":36,"area":null},{"id":"2404.17399","title":"Evaluations of Machine Learning Privacy Defenses are Misleading","created":"2024-04-26","cited_by_count":36,"area":null},{"id":"2106.15023","title":"Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent","created":"2021-06-28","cited_by_count":35,"area":null},{"id":"2107.02425","title":"GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularization","created":"2021-07-06","cited_by_count":34,"area":null},{"id":"2212.05630","title":"DISCO: Adversarial Defense with Local Implicit Functions","created":"2022-12-11","cited_by_count":34,"area":null},{"id":"2105.10304","title":"Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks","created":"2021-05-21","cited_by_count":33,"area":null},{"id":"2411.18948","title":"RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis","created":"2024-11-28","cited_by_count":33,"area":"rag"},{"id":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","cited_by_count":32,"area":null},{"id":"2509.22830","title":"ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents","created":"2025-09-26","cited_by_count":31,"area":"agents"},{"id":"2601.17548","title":"Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems","created":"2026-01-24","cited_by_count":31,"area":"agents"},{"id":"2103.03000","title":"SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain","created":"2021-03-04","cited_by_count":30,"area":null},{"id":"2210.00960","title":"Stability Analysis and Generalization Bounds of Adversarial Training","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2102.02956","title":"DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks","created":"2021-02-05","cited_by_count":29,"area":null},{"id":"2102.07861","title":"Low Curvature Activations Reduce Overfitting in Adversarial Training","created":"2021-02-15","cited_by_count":29,"area":null},{"id":"2110.14068","title":"Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks","created":"2021-10-26","cited_by_count":29,"area":null},{"id":"2402.14015","title":"Corrective Machine Unlearning","created":"2024-02-21","cited_by_count":29,"area":"safety"},{"id":"2103.14347","title":"Combating Adversaries with Anti-Adversaries","created":"2021-03-26","cited_by_count":27,"area":null},{"id":"2306.10426","title":"Understanding Certified Training with Interval Bound Propagation","created":"2023-06-17","cited_by_count":26,"area":null},{"id":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2410.15362","title":"Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models","created":"2024-10-20","cited_by_count":25,"area":"alignment"},{"id":"2108.11168","title":"Adversarially Robust One-class Novelty Detection","created":"2021-08-25","cited_by_count":24,"area":null},{"id":"2110.06850","title":"Boosting the Certified Robustness of L-infinity Distance Nets","created":"2021-10-13","cited_by_count":24,"area":null},{"id":"2204.04636","title":"\"That Is a Suspicious Reaction!\": Interpreting Logits Variation to Detect NLP Adversarial Attacks","created":"2022-04-10","cited_by_count":24,"area":null},{"id":"2207.08089","title":"Threat Model-Agnostic Adversarial Defense using Diffusion Models","created":"2022-07-17","cited_by_count":24,"area":"diffusion"},{"id":"2408.00315","title":"ADBM: Adversarial diffusion bridge model for reliable adversarial purification","created":"2024-08-01","cited_by_count":24,"area":"diffusion"},{"id":"2105.12508","title":"Adversarial Robustness against Multiple and Single $l_p$-Threat Models via Quick Fine-Tuning of Robust Classifiers","created":"2021-05-26","cited_by_count":23,"area":null},{"id":"2106.09947","title":"Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples","created":"2021-06-18","cited_by_count":23,"area":null},{"id":"2206.03393","title":"Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition","created":"2022-06-07","cited_by_count":23,"area":null},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2303.01507","title":"Defending against Adversarial Audio via Diffusion Model","created":"2023-03-02","cited_by_count":23,"area":"diffusion"},{"id":"2102.11860","title":"Automated Discovery of Adaptive Attacks on Adversarial Defenses","created":"2021-02-23","cited_by_count":22,"area":null},{"id":"2102.13624","title":"What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning","created":"2021-02-26","cited_by_count":22,"area":"safety"},{"id":"2111.13844","title":"Adaptive Image Transformations for Transfer-based Adversarial Attack","created":"2021-11-27","cited_by_count":22,"area":null},{"id":"2202.01811","title":"ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking","created":"2022-02-03","cited_by_count":22,"area":null}],"next_cursor":"100"}