mlsanityData to 7 Oct 2026

Assessing Adversarial Robustness of Large Language Models: An Empirical Study

arXiv 2405.02764 ↗First posted 4 May 2024cs.CL cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes vulnerabilities in leading open-source LLMs, including Llama, OPT, and T5. We assess the impact of model size, structure, and fine-tuning strategies on their resistance to adversarial perturbations. Our comprehensive evaluation across five diverse text classification tasks establishes a new benchmark for LLM robustness. The findings of this study have far-reaching implications for the reliable deployment of LLMs in real-world applications and contribute to the advancement of trustworthy AI systems.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 4 May 2024.

Builds on

28 of 42 references.

References · 28

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  6. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  7. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  8. 2018Deep contextualized word representationscited by 2,285
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  10. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 881
  11. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  12. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 798
16 more
  1. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  2. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  3. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 505
  4. 2018Generating Natural Language Adversarial Examplescited by 422
  5. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 376
  6. 2023On Evaluating Adversarial Robustness of Large Vision-Language Modelscited by 281
  7. 2023Sentiment Analysis in the Era of Large Language Models: A Reality Checkcited by 262
  8. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 233
  9. 2021Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Modelscited by 227
  10. 2023Benchmarking Foundation Models with Language-Model-as-an-Examinercited by 172
  11. 2023Is ChatGPT a Good Sentiment Analyzer? A Preliminary Studycited by 96
  12. 2022DDXPlus: A New Dataset For Automatic Medical Diagnosiscited by 87
  13. 2021AEDA: An Easier Data Augmentation Technique for Text Classificationcited by 67
  14. 2020Generating Fluent Adversarial Examples for Natural Languagescited by 49
  15. 2020A Geometry-Inspired Attack for Generating Natural Language Adversarial Examplescited by 20
  16. 2021Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attackscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 10; 2026: 8.

21 papers.

Sort:

By area:

  1. 2024Adversarial Attacks on Large Language Models Using Regularized Relaxationcited by 12
  2. 2025Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metricscited by 12
  3. 2024Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerationscited by 8
  4. 2025Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocolcited by 6
  5. 2025DICE: A Framework for Dimensional and Contextual Evaluation of Language Modelscited by 3
  6. 2025Adversarial Attack on Large Language Models using Exponentiated Gradient Descentcited by 3
  7. 2025Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMscited by 2
  8. 2025Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descentcited by 2
  9. 2026Robustness as an Emergent Property of Task Performancecited by 2
  10. 2025Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approachcited by 1
  11. 2026Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysiscited by 1
  12. 2024On Adversarial Robustness of Language Models in Transfer Learningcited by 0
9 more
  1. 2025Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradoxcited by 0
  2. 2025Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attackscited by 0
  3. 2025Uncovering Competency Gaps in Large Language Models and Their Benchmarkscited by 0
  4. 2026AIDG: A Formal Decomposition of Information Extraction and Containment Asymmetries in Multi-Turn LLM Dialoguecited by 0
  5. 2026ORACAL: A Robust and Explainable Multimodal Framework for Smart Contract Vulnerability Detection with Causal Graph Enrichmentcited by 0
  6. 2026Are LLMs Ready for Conflict Monitoring? Empirical Evidence from West Africacited by 0
  7. 2026TriEval: A Resource-Efficient Pipeline for LLM Bias, Toxicity, and Truthfulness Assessmentcited by 0
  8. 2026S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLPcited by 0
  9. 2026LAAF: A Layered Accountability Architecture Framework for LLM Applicationscited by 0