# Position: Adversarial ML for LLMs Is Not Making Any Progress

arXiv: https://arxiv.org/abs/2502.02260 · HTML: https://mlsanity.com/paper/2502.02260/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 76 of its 101 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Builds on (most cited first, 30 of 76)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Deduplicating Training Data Makes Language Models Better](https://mlsanity.com/paper/2107.06499/) (2021)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)

## Built on by (most cited first, 15 of 15)

- [When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review](https://mlsanity.com/paper/2509.09912/) (2025)
- [Shaping capabilities with token-level data filtering](https://mlsanity.com/paper/2601.21571/) (2026)
- [Adversarial Tokenization](https://mlsanity.com/paper/2503.02174/) (2025)
- [Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives](https://mlsanity.com/paper/2502.11910/) (2025)
- [Benchmarking Misuse Mitigation Against Covert Adversaries](https://mlsanity.com/paper/2506.06414/) (2025)
- [Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval](https://mlsanity.com/paper/2505.15753/) (2025)
- [AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research](https://mlsanity.com/paper/2511.04316/) (2025)
- [One Token Embedding Is Enough to Deadlock Your Large Reasoning Model](https://mlsanity.com/paper/2510.15965/) (2025)
- [Memory poisoning and secure multi-agent systems](https://mlsanity.com/paper/2603.20357/) (2026)
- [Intent Laundering: AI Safety Datasets Are Not What They Seem](https://mlsanity.com/paper/2602.16729/) (2026)
- [A Red Teaming Roadmap Towards System-Level Safety](https://mlsanity.com/paper/2506.05376/) (2025)
- [Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems](https://mlsanity.com/paper/2512.23132/) (2025)
- [`A la recherche du sens perdu: your favourite LLM might have more to say than you can understand](https://mlsanity.com/paper/2503.00224/) (2025)
- [Keep It Real: Challenges in Attacking Compression-Based Adversarial Purification](https://mlsanity.com/paper/2508.05489/) (2025)
- [An Investigation of the NeurIPS and ICML 2025 Position Tracks](https://mlsanity.com/paper/2608.16894/) (2026)

## Abstract (arXiv)

In the past decade, considerable research effort has been devoted to securing machine learning (ML) models that operate in adversarial settings. Yet, progress has been slow even for simple "toy" problems (e.g., robustness to small adversarial perturbations) and is often hindered by non-rigorous evaluations. Today, adversarial ML research has shifted towards studying larger, general-purpose language models. In this position paper, we argue that the situation is now even worse: in the era of LLMs, the field of adversarial ML studies problems that are (1) less clearly defined, (2) harder to solve, and (3) even more challenging to evaluate. As a result, we caution that yet another decade of work on adversarial ML may be failing to produce meaningful progress.