{"total":59,"rows":[{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2306.09194","title":"Undetectable Watermarks for Language Models","created":"2023-05-25","cited_by_count":226,"area":"safety"},{"id":"2307.14692","title":"Backdoor Attacks for In-Context Learning with Language Models","created":"2023-07-27","cited_by_count":96,"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":"2206.01295","title":"Rashomon Capacity: A Metric for Predictive Multiplicity in Classification","created":"2022-06-02","cited_by_count":47,"area":null},{"id":"2211.12681","title":"Benchmarking Adversarially Robust Quantum Machine Learning at Scale","created":"2022-11-23","cited_by_count":29,"area":null},{"id":"2310.18933","title":"Label Poisoning is All You Need","created":"2023-10-29","cited_by_count":29,"area":"safety"},{"id":"2209.15259","title":"On the Impossible Safety of Large AI Models","created":"2022-09-30","cited_by_count":28,"area":null},{"id":"2206.07840","title":"Architectural Backdoors in Neural Networks","created":"2022-06-15","cited_by_count":25,"area":null},{"id":"2302.12461","title":"Analyzing And Editing Inner Mechanisms Of Backdoored Language Models","created":"2023-02-24","cited_by_count":23,"area":"safety"},{"id":"2307.00682","title":"Tools for Verifying Neural Models' Training Data","created":"2023-07-02","cited_by_count":22,"area":null},{"id":"2401.17975","title":"Understanding polysemanticity in neural networks through coding theory","created":"2024-01-31","cited_by_count":17,"area":null},{"id":"2210.05929","title":"Few-shot Backdoor Attacks via Neural Tangent Kernels","created":"2022-10-12","cited_by_count":15,"area":null},{"id":"2404.04500","title":"Trustless Audits without Revealing Data or Models","created":"2024-04-06","cited_by_count":15,"area":null},{"id":"2307.10163","title":"Rethinking Backdoor Attacks","created":"2023-07-19","cited_by_count":14,"area":"safety"},{"id":"2303.00215","title":"Single Image Backdoor Inversion via Robust Smoothed Classifiers","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2210.00108","title":"ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks","created":"2022-09-30","cited_by_count":9,"area":null},{"id":"2409.00399","title":"Rethinking Backdoor Detection Evaluation for Language Models","created":"2024-08-31","cited_by_count":9,"area":"lr"},{"id":"2412.06219","title":"Data Free Backdoor Attacks","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2212.11415","title":"Circumventing interpretability: How to defeat mind-readers","created":"2022-12-21","cited_by_count":6,"area":null},{"id":"2302.09578","title":"On Feasibility of Server-side Backdoor Attacks on Split Learning","created":"2023-02-19","cited_by_count":6,"area":null},{"id":"2511.02620","title":"Verifying LLM Inference to Detect Model Weight Exfiltration","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2205.09986","title":"SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learning","created":"2022-05-20","cited_by_count":5,"area":null},{"id":"2505.19532","title":"Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning","created":"2025-05-26","cited_by_count":5,"area":"deeprl"},{"id":"2406.02619","title":"Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits","created":"2024-06-03","cited_by_count":4,"area":"safety"},{"id":"2312.06488","title":"Performance-lossless Black-box Model Watermarking","created":"2023-12-11","cited_by_count":3,"area":"safety"},{"id":"2404.03272","title":"Cryptographic Hardness of Score Estimation","created":"2024-04-04","cited_by_count":3,"area":null},{"id":"2406.05660","title":"Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models","created":"2024-06-09","cited_by_count":3,"area":"safety"},{"id":"2409.17328","title":"The poison of dimensionality","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2512.10100","title":"Robust AI Security and Alignment: A Sisyphean Endeavor?","created":"2025-12-10","cited_by_count":3,"area":null},{"id":"2602.16984","title":"Fundamental Limits of Black-Box Safety Evaluation: Information-Theoretic and Computational Barriers from Latent Context Conditioning","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2308.03999","title":"Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoning","created":"2023-08-08","cited_by_count":2,"area":"lr"},{"id":"2409.03077","title":"Backdoor defense, learnability and obfuscation","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2505.13708","title":"Robust learning of halfspaces under log-concave marginals","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2509.20714","title":"Cryptographic Backdoor for Neural Networks: Boon and Bane","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2511.09493","title":"Consensus Sampling for Safer Generative AI","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2210.06509","title":"Understanding Impacts of Task Similarity on Backdoor Attack and Detection","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2305.09671","title":"Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks","created":"2023-05-07","cited_by_count":1,"area":"safety"},{"id":"2503.17578","title":"Large Language Models Can Verbatim Reproduce Long Malicious Sequences","created":"2025-03-21","cited_by_count":1,"area":"safety"},{"id":"2504.20310","title":"A Cryptographic Perspective on Mitigation vs. Detection in Machine Learning","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2510.06527","title":"Wide Neural Networks as a Baseline for the Computational No-Coincidence Conjecture","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2512.04008","title":"Efficient Public Verification of Private ML via Regularization","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2603.25861","title":"Why Safety Probes Catch Liars But Miss Fanatics","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2607.09532","title":"Statistically Undetectable Backdoors in Deep Neural Networks","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2212.06576","title":"AI Model Utilization Measurements For Finding Class Encoding Patterns","created":"2022-12-12","cited_by_count":0,"area":null},{"id":"2301.07474","title":"Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomy","created":"2023-01-18","cited_by_count":0,"area":null},{"id":"2405.13217","title":"Interactive Simulations of Backdoors in Neural Networks","created":"2024-05-21","cited_by_count":0,"area":null},{"id":"2411.13047","title":"Bounding-box Watermarking: Defense against Model Extraction Attacks on Object Detectors","created":"2024-11-20","cited_by_count":0,"area":"safety"},{"id":"2505.08138","title":"Mirror Mirror on the Wall, Have I Forgotten it All? A New Framework for Evaluating Machine Unlearning","created":"2025-05-13","cited_by_count":0,"area":"safety"},{"id":"2603.10641","title":"Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2605.13214","title":"Backdoor Channels Hidden in Latent Space: Extending Cryptographic Undetectability to Modern Neural Networks","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.30423","title":"Proofs of Ownership for Machine Learning Models","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.00543","title":"Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor","created":"2026-08-01","cited_by_count":0,"area":"diffusion"},{"id":"2609.16403","title":"Implementing a White-Box Undetectable Backdoor for Random Fourier Features","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.21515","title":"ServeGuard: Verifiable, Bounded-Residual Confinement of Operator-Invisible Channels Without Revealing the Certified Read Factor","created":"2026-09-18","cited_by_count":0,"area":"safety"},{"id":"2609.36117","title":"Why Backdooring Neural Networks is so Easy?","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39768","title":"Security Properties of Neural Networks as Decision Problems","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.13051","title":"Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13928","title":"AI Models Can Provably Hide Arbitrary Capabilities","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}