{"total":264,"rows":[{"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":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"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":"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":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320,"area":null},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232,"area":null},{"id":"2309.14348","title":"Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM","created":"2023-09-18","cited_by_count":192,"area":"alignment"},{"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":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170,"area":null},{"id":"2212.00638","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","created":"2022-12-01","cited_by_count":150,"area":null},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147,"area":null},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141,"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":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2405.15589","title":"Efficient Adversarial Training in LLMs with Continuous Attacks","created":"2024-05-24","cited_by_count":113,"area":"safety"},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111,"area":null},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108,"area":null},{"id":"2106.07345","title":"Self-Guided Contrastive Learning for BERT Sentence Representations","created":"2021-06-03","cited_by_count":103,"area":null},{"id":"2210.10683","title":"Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP","created":"2022-10-19","cited_by_count":102,"area":null},{"id":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101,"area":null},{"id":"2310.05914","title":"NEFTune: Noisy Embeddings Improve Instruction Finetuning","created":"2023-10-09","cited_by_count":100,"area":null},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2402.09063","title":"Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space","created":"2024-02-14","cited_by_count":91,"area":"alignment"},{"id":"2405.20978","title":"Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training","created":"2024-05-31","cited_by_count":89,"area":"lr"},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88,"area":"safety"},{"id":"2210.01765","title":"One Transformer Can Understand Both 2D & 3D Molecular Data","created":"2022-10-04","cited_by_count":77,"area":null},{"id":"2112.12376","title":"Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization","created":"2021-12-23","cited_by_count":76,"area":null},{"id":"2204.00993","title":"Improving Vision Transformers by Revisiting High-frequency Components","created":"2022-04-03","cited_by_count":76,"area":null},{"id":"2105.11144","title":"Improved OOD Generalization via Adversarial Training and Pre-training","created":"2021-05-24","cited_by_count":66,"area":null},{"id":"2409.20089","title":"Robust LLM safeguarding via refusal feature adversarial training","created":"2024-09-30","cited_by_count":64,"area":null},{"id":"2105.03743","title":"Certified Robustness to Text Adversarial Attacks by Randomized [MASK]","created":"2021-05-08","cited_by_count":57,"area":null},{"id":"2112.07869","title":"Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing","created":"2021-12-15","cited_by_count":57,"area":null},{"id":"2108.12777","title":"Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution","created":"2021-08-29","cited_by_count":56,"area":null},{"id":"2205.00656","title":"Debiased Contrastive Learning of Unsupervised Sentence Representations","created":"2022-05-02","cited_by_count":56,"area":null},{"id":"2107.00440","title":"CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding","created":"2021-07-01","cited_by_count":50,"area":null},{"id":"2101.06560","title":"Adversarial Attacks On Multi-Agent Communication","created":"2021-01-17","cited_by_count":49,"area":null},{"id":"2207.01164","title":"Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations","created":"2022-07-04","cited_by_count":46,"area":null},{"id":"2203.11528","title":"Out-of-distribution Generalization with Causal Invariant Transformations","created":"2022-03-22","cited_by_count":45,"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":"2106.08226","title":"Consistency Regularization for Cross-Lingual Fine-Tuning","created":"2021-06-15","cited_by_count":41,"area":null},{"id":"2112.02732","title":"JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering","created":"2021-12-06","cited_by_count":40,"area":null},{"id":"2106.08062","title":"SSMix: Saliency-Based Span Mixup for Text Classification","created":"2021-06-15","cited_by_count":39,"area":null},{"id":"2107.10137","title":"Improved Text Classification via Contrastive Adversarial Training","created":"2021-07-21","cited_by_count":38,"area":null},{"id":"2305.17826","title":"NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models","created":"2023-05-28","cited_by_count":37,"area":"safety"},{"id":"2106.01810","title":"Defending Against Backdoor Attacks in Natural Language Generation","created":"2021-06-03","cited_by_count":33,"area":"safety"},{"id":"2106.00149","title":"HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization","created":"2021-05-31","cited_by_count":32,"area":null},{"id":"2107.04835","title":"Noise Stability Regularization for Improving BERT Fine-tuning","created":"2021-07-10","cited_by_count":29,"area":null},{"id":"2103.00397","title":"Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective","created":"2021-02-28","cited_by_count":25,"area":null},{"id":"2104.05062","title":"Achieving Model Robustness through Discrete Adversarial Training","created":"2021-04-11","cited_by_count":23,"area":null},{"id":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23,"area":null},{"id":"2209.07735","title":"Enhance the Visual Representation via Discrete Adversarial Training","created":"2022-09-16","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":"2211.09359","title":"How to Fine-Tune Vision Models with SGD","created":"2022-11-17","cited_by_count":23,"area":null},{"id":"2412.03597","title":"The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2103.08933","title":"Reweighting Augmented Samples by Minimizing the Maximal Expected Loss","created":"2021-03-16","cited_by_count":21,"area":null},{"id":"2110.03192","title":"GNN is a Counter? Revisiting GNN for Question Answering","created":"2021-10-07","cited_by_count":21,"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":"2211.02878","title":"Textual Manifold-based Defense Against Natural Language Adversarial Examples","created":"2022-11-05","cited_by_count":19,"area":null},{"id":"2306.01505","title":"Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations","created":"2023-06-02","cited_by_count":19,"area":null},{"id":"2307.10235","title":"Towards Viewpoint-Invariant Visual Recognition via Adversarial Training","created":"2023-07-16","cited_by_count":19,"area":null},{"id":"2404.15081","title":"Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models","created":"2024-04-23","cited_by_count":18,"area":"diffusion"},{"id":"2105.11776","title":"Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering","created":"2021-05-25","cited_by_count":17,"area":null},{"id":"2206.05511","title":"Improving the Adversarial Robustness of NLP Models by Information Bottleneck","created":"2022-06-11","cited_by_count":17,"area":null},{"id":"2303.12320","title":"GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering","created":"2023-03-22","cited_by_count":17,"area":"lr"},{"id":"2112.10991","title":"Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement","created":"2021-12-21","cited_by_count":16,"area":null},{"id":"2206.02457","title":"Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2211.03013","title":"Robust Lottery Tickets for Pre-trained Language Models","created":"2022-11-06","cited_by_count":16,"area":null},{"id":"2404.12274","title":"Advancing the Robustness of Large Language Models through Self-Denoised Smoothing","created":"2024-04-18","cited_by_count":16,"area":"safety"},{"id":"2410.02163","title":"Adversarial Decoding: Generating Readable Documents for Adversarial Objectives","created":"2024-10-03","cited_by_count":16,"area":"safety"},{"id":"2101.05509","title":"Transformer-based Language Model Fine-tuning Methods for COVID-19 Fake News Detection","created":"2021-01-14","cited_by_count":15,"area":null},{"id":"2107.11252","title":"Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation","created":"2021-07-23","cited_by_count":15,"area":null},{"id":"2109.02905","title":"Exploiting Reasoning Chains for Multi-hop Science Question Answering","created":"2021-09-07","cited_by_count":15,"area":null},{"id":"2110.03313","title":"Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2110.14855","title":"CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks","created":"2021-10-28","cited_by_count":15,"area":null},{"id":"2203.10378","title":"On Robust Prefix-Tuning for Text Classification","created":"2022-03-19","cited_by_count":15,"area":null},{"id":"2205.06153","title":"TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding","created":"2022-05-12","cited_by_count":15,"area":null},{"id":"2210.02952","title":"Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation","created":"2022-10-06","cited_by_count":15,"area":null},{"id":"2305.02423","title":"PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer","created":"2023-05-03","cited_by_count":15,"area":null},{"id":"2407.06992","title":"Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective","created":"2024-07-09","cited_by_count":15,"area":null},{"id":"2202.02771","title":"Optimal Algorithms for Decentralized Stochastic Variational Inequalities","created":"2022-02-06","cited_by_count":14,"area":null},{"id":"2202.13840","title":"Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks","created":"2022-02-28","cited_by_count":13,"area":null},{"id":"2207.08374","title":"Adversarial Contrastive Learning via Asymmetric InfoNCE","created":"2022-07-18","cited_by_count":13,"area":null},{"id":"2110.08419","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","created":"2021-10-16","cited_by_count":12,"area":null},{"id":"2204.13846","title":"RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning","created":"2022-04-29","cited_by_count":12,"area":null},{"id":"2206.05658","title":"Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization","created":"2022-06-12","cited_by_count":12,"area":null},{"id":"2405.00256","title":"ASAM: Boosting Segment Anything Model with Adversarial Tuning","created":"2024-05-01","cited_by_count":12,"area":null},{"id":"2103.12171","title":"Adversarial Feature Augmentation and Normalization for Visual Recognition","created":"2021-03-22","cited_by_count":11,"area":null},{"id":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","cited_by_count":11,"area":null},{"id":"2305.06522","title":"Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications","created":"2023-05-11","cited_by_count":11,"area":null},{"id":"2105.13608","title":"Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax","created":"2021-05-28","cited_by_count":10,"area":null},{"id":"2205.11603","title":"Representation Projection Invariance Mitigates Representation Collapse","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2207.05641","title":"Backdoor Attacks on Crowd Counting","created":"2022-07-12","cited_by_count":10,"area":null},{"id":"2305.04557","title":"Toward Adversarial Training on Contextualized Language Representation","created":"2023-05-08","cited_by_count":10,"area":null},{"id":"2311.17400","title":"Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention","created":"2023-11-29","cited_by_count":10,"area":null},{"id":"2108.13048","title":"ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding","created":"2021-08-30","cited_by_count":9,"area":null},{"id":"2110.07165","title":"Semantically Distributed Robust Optimization for Vision-and-Language Inference","created":"2021-10-14","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":"2303.07320","title":"Model-tuning Via Prompts Makes NLP Models Adversarially Robust","created":"2023-03-13","cited_by_count":9,"area":null}],"next_cursor":"100"}