{"total":447,"rows":[{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"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":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284,"area":"mllm"},{"id":"2104.02610","title":"On the Robustness of Vision Transformers to Adversarial Examples","created":"2021-03-31","cited_by_count":167,"area":null},{"id":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158,"area":null},{"id":"2202.10103","title":"Robustness and Accuracy Could Be Reconcilable by (Proper) Definition","created":"2022-02-21","cited_by_count":111,"area":null},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2205.01992","title":"Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning","created":"2022-05-04","cited_by_count":94,"area":"safety"},{"id":"2204.00008","title":"Improving Adversarial Transferability via Neuron Attribution-Based Attacks","created":"2022-03-31","cited_by_count":93,"area":null},{"id":"2201.05057","title":"On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles","created":"2022-01-13","cited_by_count":90,"area":null},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"area":"offlinerl"},{"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":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"area":null},{"id":"2403.01218","title":"Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy","created":"2024-03-02","cited_by_count":82,"area":"safety"},{"id":"2403.06833","title":"Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?","created":"2024-03-11","cited_by_count":81,"area":null},{"id":"2201.12296","title":"Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions","created":"2022-01-28","cited_by_count":80,"area":null},{"id":"2109.00544","title":"Towards Improving Adversarial Training of NLP Models","created":"2021-09-01","cited_by_count":79,"area":null},{"id":"2109.05211","title":"RobustART: Benchmarking Robustness on Architecture Design and Training Techniques","created":"2021-09-11","cited_by_count":79,"area":null},{"id":"2111.02813","title":"WaveFake: A Data Set to Facilitate Audio Deepfake Detection","created":"2021-11-04","cited_by_count":78,"area":null},{"id":"2410.08827","title":"Do Unlearning Methods Remove Information from Language Model Weights?","created":"2024-10-11","cited_by_count":73,"area":"safety"},{"id":"2401.11170","title":"Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images","created":"2024-01-20","cited_by_count":69,"area":"mllm"},{"id":"2202.13711","title":"Evaluating the Adversarial Robustness of Adaptive Test-time Defenses","created":"2022-02-28","cited_by_count":64,"area":null},{"id":"2106.07904","title":"Probabilistic Margins for Instance Reweighting in Adversarial Training","created":"2021-06-15","cited_by_count":57,"area":null},{"id":"2212.14315","title":"\"Real Attackers Don't Compute Gradients\": Bridging the Gap Between Adversarial ML Research and Practice","created":"2022-12-29","cited_by_count":56,"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":"2402.09674","title":"PAL: Proxy-Guided Black-Box Attack on Large Language Models","created":"2024-02-15","cited_by_count":50,"area":"safety"},{"id":"2111.09277","title":"SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness","created":"2021-11-17","cited_by_count":49,"area":null},{"id":"2209.08744","title":"AdvDO: Realistic Adversarial Attacks for Trajectory Prediction","created":"2022-09-19","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":"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":"2101.06784","title":"Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving","created":"2021-01-17","cited_by_count":45,"area":null},{"id":"2111.04314","title":"Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning","created":"2021-11-08","cited_by_count":44,"area":null},{"id":"2411.18688","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","created":"2024-11-27","cited_by_count":44,"area":"lr"},{"id":"2504.14348","title":"Manipulating Multimodal Agents via Cross-Modal Prompt Injection","created":"2025-04-19","cited_by_count":44,"area":"mllm"},{"id":"2101.09617","title":"A Comprehensive Evaluation Framework for Deep Model Robustness","created":"2021-01-24","cited_by_count":42,"area":null},{"id":"2103.05134","title":"Constrained Learning with Non-Convex Losses","created":"2021-03-08","cited_by_count":42,"area":null},{"id":"2207.07972","title":"Certified Neural Network Watermarks with Randomized Smoothing","created":"2022-07-16","cited_by_count":41,"area":null},{"id":"2601.04603","title":"Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks","created":"2026-01-08","cited_by_count":41,"area":"safety"},{"id":"2103.03344","title":"WaveGuard: Understanding and Mitigating Audio Adversarial Examples","created":"2021-03-04","cited_by_count":40,"area":null},{"id":"2110.15767","title":"Adversarial Robustness with Semi-Infinite Constrained Learning","created":"2021-10-29","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":"2411.15720","title":"Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks","created":"2024-11-24","cited_by_count":39,"area":"mllm"},{"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":"2112.07668","title":"Dual-Key Multimodal Backdoors for Visual Question Answering","created":"2021-12-14","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":"2303.15735","title":"Improving the Transferability of Adversarial Samples by Path-Augmented Method","created":"2023-03-28","cited_by_count":36,"area":null},{"id":"2405.03658","title":"A review on data-driven constitutive laws for solids","created":"2024-05-06","cited_by_count":35,"area":null},{"id":"2106.02105","title":"A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks","created":"2021-06-03","cited_by_count":34,"area":null},{"id":"2207.09504","title":"Invariant Feature Learning for Generalized Long-Tailed Classification","created":"2022-07-19","cited_by_count":34,"area":null},{"id":"2409.14586","title":"Backtracking Improves Generation Safety","created":"2024-09-22","cited_by_count":32,"area":"alignment"},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2210.00933","title":"Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2102.10454","title":"On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning","created":"2021-02-20","cited_by_count":29,"area":null},{"id":"2104.01575","title":"Reliably fast adversarial training via latent adversarial perturbation","created":"2021-04-04","cited_by_count":29,"area":null},{"id":"2211.00241","title":"Adversarial Policies Beat Superhuman Go AIs","created":"2022-11-01","cited_by_count":29,"area":null},{"id":"2210.10253","title":"On the Adversarial Robustness of Mixture of Experts","created":"2022-10-19","cited_by_count":28,"area":"moe"},{"id":"2103.14347","title":"Combating Adversaries with Anti-Adversaries","created":"2021-03-26","cited_by_count":27,"area":null},{"id":"2107.14110","title":"Enhancing Adversarial Robustness via Test-time Transformation Ensembling","created":"2021-07-29","cited_by_count":27,"area":null},{"id":"2106.11022","title":"Hard Choices in Artificial Intelligence","created":"2021-06-10","cited_by_count":26,"area":null},{"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":"2104.09284","title":"LAFEAT: Piercing Through Adversarial Defenses with Latent Features","created":"2021-04-19","cited_by_count":24,"area":null},{"id":"2106.11072","title":"Techniques for Symbol Grounding with SATNet","created":"2021-06-16","cited_by_count":24,"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":"2209.14105","title":"Exploring the Relationship between Architecture and Adversarially Robust Generalization","created":"2022-09-28","cited_by_count":23,"area":null},{"id":"2405.09981","title":"Adversarial Robustness for Visual Grounding of Multimodal Large Language Models","created":"2024-05-16","cited_by_count":23,"area":"mllm"},{"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":"2112.01156","title":"A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space","created":"2021-12-02","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},{"id":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2401.10899","title":"Concrete Problems in AI Safety, Revisited","created":"2023-12-18","cited_by_count":22,"area":null},{"id":"2510.13237","title":"Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models","created":"2025-10-15","cited_by_count":22,"area":"vla"},{"id":"2210.06433","title":"Self-supervised video pretraining yields robust and more human-aligned visual representations","created":"2022-10-12","cited_by_count":20,"area":null},{"id":"2210.09852","title":"Scaling Adversarial Training to Large Perturbation Bounds","created":"2022-10-18","cited_by_count":20,"area":null},{"id":"2212.01806","title":"Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networks","created":"2022-12-04","cited_by_count":18,"area":null},{"id":"2101.04829","title":"On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attacks","created":"2021-01-13","cited_by_count":17,"area":null},{"id":"2103.14211","title":"MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes","created":"2021-03-26","cited_by_count":17,"area":null},{"id":"2106.10606","title":"Attack to Fool and Explain Deep Networks","created":"2021-06-20","cited_by_count":17,"area":null},{"id":"2207.00244","title":"Discriminator-Guided Model-Based Offline Imitation Learning","created":"2022-07-01","cited_by_count":17,"area":"offlinerl"},{"id":"2302.02300","title":"Run-Off Election: Improved Provable Defense against Data Poisoning Attacks","created":"2023-02-05","cited_by_count":17,"area":"safety"},{"id":"2501.14959","title":"Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learning","created":"2025-01-24","cited_by_count":17,"area":null},{"id":"2208.09801","title":"PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition","created":"2022-08-21","cited_by_count":16,"area":null},{"id":"2303.13846","title":"Feature Separation and Recalibration for Adversarial Robustness","created":"2023-03-24","cited_by_count":16,"area":null},{"id":"2103.03438","title":"Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack","created":"2021-03-05","cited_by_count":15,"area":null},{"id":"2201.04018","title":"Feature Space Hijacking Attacks against Differentially Private Split Learning","created":"2022-01-11","cited_by_count":15,"area":null},{"id":"2211.09565","title":"Towards Good Practices in Evaluating Transfer Adversarial Attacks","created":"2022-11-17","cited_by_count":15,"area":null},{"id":"2306.06712","title":"Neural Architecture Design and Robustness: A Dataset","created":"2023-06-11","cited_by_count":15,"area":null},{"id":"2307.15008","title":"A LLM Assisted Exploitation of AI-Guardian","created":"2023-07-20","cited_by_count":15,"area":null},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2503.01811","title":"AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2507.07417","title":"May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks","created":"2025-07-10","cited_by_count":15,"area":"safety"},{"id":"2105.06677","title":"XAI Handbook: Towards a Unified Framework for Explainable AI","created":"2021-05-14","cited_by_count":14,"area":null},{"id":"2105.14785","title":"Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart","created":"2021-05-31","cited_by_count":14,"area":null},{"id":"2107.04263","title":"Towards Robust General Medical Image Segmentation","created":"2021-07-09","cited_by_count":14,"area":null},{"id":"2206.01367","title":"Adversarial Unlearning: Reducing Confidence Along Adversarial Directions","created":"2022-06-03","cited_by_count":14,"area":"safety"},{"id":"2404.08690","title":"Towards Building a Robust Toxicity Predictor","created":"2024-04-09","cited_by_count":14,"area":null},{"id":"2404.16557","title":"Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samples","created":"2024-04-25","cited_by_count":14,"area":"mllm"}],"next_cursor":"100"}