{"total":99,"rows":[{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336,"area":null},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245,"area":null},{"id":"2303.04381","title":"Automatically Auditing Large Language Models via Discrete Optimization","created":"2023-03-08","cited_by_count":191,"area":null},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2112.08348","title":"Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts","created":"2021-12-15","cited_by_count":64,"area":null},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2110.02797","title":"Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs","created":"2021-10-06","cited_by_count":57,"area":null},{"id":"2305.10435","title":"Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions","created":"2023-05-11","cited_by_count":55,"area":null},{"id":"2202.08827","title":"LAMP: Extracting Text from Gradients with Language Model Priors","created":"2022-02-17","cited_by_count":54,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2205.01287","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","created":"2022-05-03","cited_by_count":42,"area":null},{"id":"2301.12868","title":"On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex","created":"2023-01-30","cited_by_count":41,"area":null},{"id":"2310.04444","title":"What's the Magic Word? A Control Theory of LLM Prompting","created":"2023-10-02","cited_by_count":41,"area":null},{"id":"2402.11493","title":"Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation","created":"2024-02-18","cited_by_count":38,"area":null},{"id":"2110.15317","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","created":"2021-10-28","cited_by_count":28,"area":null},{"id":"2210.17004","title":"Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution","created":"2022-10-31","cited_by_count":28,"area":null},{"id":"2312.04782","title":"Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs","created":"2023-12-08","cited_by_count":27,"area":null},{"id":"2210.02912","title":"CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning","created":"2022-10-06","cited_by_count":24,"area":null},{"id":"2212.09254","title":"TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization","created":"2022-12-19","cited_by_count":21,"area":null},{"id":"2310.04445","title":"LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model","created":"2023-10-02","cited_by_count":21,"area":null},{"id":"2405.02764","title":"Assessing Adversarial Robustness of Large Language Models: An Empirical Study","created":"2024-05-04","cited_by_count":21,"area":null},{"id":"2401.00529","title":"GraphGPT: Generative Pre-trained Graph Eulerian Transformer","created":"2023-12-31","cited_by_count":17,"area":null},{"id":"2402.01806","title":"HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text","created":"2024-02-02","cited_by_count":16,"area":null},{"id":"2405.02466","title":"ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models","created":"2024-05-03","cited_by_count":16,"area":null},{"id":"2205.01094","title":"A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictions","created":"2022-05-01","cited_by_count":15,"area":null},{"id":"2404.17475","title":"CEval: A Benchmark for Evaluating Counterfactual Text Generation","created":"2024-04-26","cited_by_count":15,"area":null},{"id":"2305.03655","title":"White-Box Multi-Objective Adversarial Attack on Dialogue Generation","created":"2023-05-05","cited_by_count":14,"area":null},{"id":"2302.00944","title":"TransFool: An Adversarial Attack against Neural Machine Translation Models","created":"2023-02-02","cited_by_count":12,"area":null},{"id":"2408.05446","title":"Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness","created":"2024-08-08","cited_by_count":12,"area":null},{"id":"2410.19160","title":"Adversarial Attacks on Large Language Models Using Regularized Relaxation","created":"2024-10-24","cited_by_count":12,"area":null},{"id":"2404.17120","title":"Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputs","created":"2024-04-26","cited_by_count":11,"area":null},{"id":"2505.15433","title":"Set-LLM: A Permutation-Invariant LLM","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2402.11083","title":"VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models","created":"2024-02-16","cited_by_count":10,"area":null},{"id":"2501.15509","title":"FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint","created":"2025-01-26","cited_by_count":10,"area":null},{"id":"2203.05948","title":"Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers","created":"2022-03-11","cited_by_count":9,"area":null},{"id":"2302.02568","title":"Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend","created":"2023-02-06","cited_by_count":9,"area":null},{"id":"2109.05698","title":"Detecting Textual Adversarial Examples through Randomized Substitution and Vote","created":"2021-09-13","cited_by_count":8,"area":null},{"id":"2303.08032","title":"Verifying the Robustness of Automatic Credibility Assessment","created":"2023-03-14","cited_by_count":8,"area":null},{"id":"2308.11295","title":"Uncertainty Estimation of Transformers' Predictions via Topological Analysis of the Attention Matrices","created":"2023-08-22","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2505.01177","title":"LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures","created":"2025-05-02","cited_by_count":8,"area":null},{"id":"2311.07064","title":"Prompts have evil twins","created":"2023-11-13","cited_by_count":7,"area":null},{"id":"2401.12461","title":"Fast Adversarial Training against Textual Adversarial Attacks","created":"2024-01-23","cited_by_count":7,"area":null},{"id":"2305.17440","title":"Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making","created":"2023-05-27","cited_by_count":6,"area":null},{"id":"2310.14265","title":"CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability","created":"2023-10-22","cited_by_count":6,"area":null},{"id":"2406.14545","title":"Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2412.08099","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","created":"2024-12-11","cited_by_count":6,"area":null},{"id":"2208.10251","title":"Rethinking Textual Adversarial Defense for Pre-trained Language Models","created":"2022-07-21","cited_by_count":5,"area":null},{"id":"2212.10258","title":"In and Out-of-Domain Text Adversarial Robustness via Label Smoothing","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2402.02969","title":"Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2503.04332","title":"The Challenge of Identifying the Origin of Black-Box Large Language Models","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2506.11844","title":"TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2308.15246","title":"A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation","created":"2023-08-29","cited_by_count":4,"area":null},{"id":"2310.19152","title":"BERT Lost Patience Won't Be Robust to Adversarial Slowdown","created":"2023-10-29","cited_by_count":4,"area":null},{"id":"2403.11833","title":"SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator","created":"2024-03-18","cited_by_count":4,"area":null},{"id":"2405.04346","title":"Revisiting Character-level Adversarial Attacks for Language Models","created":"2024-05-07","cited_by_count":4,"area":null},{"id":"2302.05120","title":"Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2305.04067","title":"The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples","created":"2023-05-06","cited_by_count":3,"area":null},{"id":"2309.08650","title":"Adversarial Attacks on Tables with Entity Swap","created":"2023-09-15","cited_by_count":3,"area":null},{"id":"2406.00999","title":"Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2407.11059","title":"Was it Slander? Towards Exact Inversion of Generative Language Models","created":"2024-07-10","cited_by_count":3,"area":null},{"id":"2506.18756","title":"Semantic-Preserving Prompt Hijacking: A Black-Box Adversarial Attack on Auto-Prompt Optimization","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2602.11175","title":"Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2205.00047","title":"Logically Consistent Adversarial Attacks for Soft Theorem Provers","created":"2022-04-29","cited_by_count":2,"area":null},{"id":"2303.10974","title":"Translate your gibberish: black-box adversarial attack on machine translation systems","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2408.00728","title":"CERT-ED: Certifiably Robust Text Classification for Edit Distance","created":"2024-08-01","cited_by_count":2,"area":null},{"id":"2408.13985","title":"TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models","created":"2024-08-26","cited_by_count":2,"area":null},{"id":"2412.20087","title":"On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs","created":"2024-12-28","cited_by_count":2,"area":null},{"id":"2506.02696","title":"Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.03355","title":"Robustness in Both Domains: CLIP Needs a Robust Text Encoder","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.08188","title":"GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2508.11667","title":"Guided Perturbation Sensitivity (GPS): Detecting Adversarial Text via Embedding Stability and Word Importance","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2510.08569","title":"ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2602.10134","title":"Reverse-Engineering Model Editing on Language Models","created":"2026-02-07","cited_by_count":2,"area":null},{"id":"2204.07182","title":"Analysing similarities between legal court documents using natural language processing approaches based on Transformers","created":"2022-04-14","cited_by_count":1,"area":null},{"id":"2303.11160","title":"Explaining Recommendation System Using Counterfactual Textual Explanations","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2306.08492","title":"A Relaxed Optimization Approach for Adversarial Attacks against Neural Machine Translation Models","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2402.02695","title":"Exploiting Class Probabilities for Black-box Sentence-level Attacks","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2402.09874","title":"Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks","created":"2024-02-15","cited_by_count":1,"area":null},{"id":"2504.13551","title":"Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2505.22943","title":"Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.23296","title":"Securing AI Systems: A Guide to Known Attacks and Impacts","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2508.10039","title":"Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries","created":"2025-08-10","cited_by_count":1,"area":null},{"id":"2608.18900","title":"TestifAI: Tomography-Based Testing for Deep Learning Systems","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2207.09539","title":"Revealing Secrets From Pre-trained Models","created":"2022-07-19","cited_by_count":0,"area":null},{"id":"2307.01488","title":"SCAT: Robust Self-supervised Contrastive Learning via Adversarial Training for Text Classification","created":"2023-07-04","cited_by_count":0,"area":null},{"id":"2407.05319","title":"Rethinking Targeted Adversarial Attacks For Neural Machine Translation","created":"2024-07-07","cited_by_count":0,"area":null},{"id":"2411.12473","title":"NMT-Obfuscator Attack: Ignore a sentence in translation with only one word","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2412.10805","title":"Are Language Models Agnostic to Linguistically Grounded Perturbations? A Case Study of Indic Languages","created":"2024-12-14","cited_by_count":0,"area":null},{"id":"2509.12672","title":"Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.23806","title":"Influence-Guided Concolic Testing of Transformer Robustness","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2602.11044","title":"Language Model Inversion through End-to-End Differentiation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.10842","title":"PivotAttack: Rethinking the Search Trajectory in Hard-Label Text Attacks via Pivot Words","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2605.27642","title":"Learning to Translate from Soft to Hard LLM Prompts","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.27215","title":"Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.29568","title":"OASIS: Optimizing Attacker Sequences for Hard-Label Black-Box Text Attacks","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.38802","title":"Uncovering Uncontrolled Repetition through Residual Stream Dynamics","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00689","title":"Towards Robust Numerical Claim Verification","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}