arXiv Machine Learning October 8, 2026 By Kevin Kuo, Virginia Smith, Chhavi Yadav

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks

Read the original on arXiv Machine Learning →

The paper examines the vulnerability of open‑weight large language model safeguards that aim to block harmful usage by assuming new harmful behavior arises only through fine‑tuning. It demonstrates that simple, low‑cost attacks—abliteration and prefilling—can significantly increase attack success rates across multiple benchmarks, and proposes an abliteration‑resistant tuning (ART) method that mitigates these attacks. The study shows that safeguarding defenses must be evaluated against a broader range of attack strategies beyond fine‑tuning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

6d ago

A Few Steps Further: Why Defenses Against Malicious Finetuning Erode Under Continued Training

arXiv:2605.14605v3 Announce Type: replace-cross Abstract: Model providers increasingly release the weights of large language models. Although these models are safety-aligned before release, their saf...

By Itay Zloczower, Eyal Lenga, Gilad Gressel, Yisroel Mirsky

llms fine-tuning safety

arXiv AI

Jun 4

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering

arXiv:2602. 06911v2 Announce Type: replace-cross Abstract: As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks.

By Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla

llms fine-tuning benchmarks safety

arXiv AI

Jun 2

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

arXiv:2603. 24511v2 Announce Type: replace-cross Abstract: We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injection evaluations.

By Alexander Panfilov, Peter Romov, Igor Shilov, Yves-Alexandre de Montjoye, Jonas Geiping, Maksym Andriushchenko

llms agents multimodal benchmarks safety

arXiv AI

Aug 7

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

arXiv:2512. 14751v3 Announce Type: replace-cross Abstract: Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications.

By Yixin Tan, Zhe Yu, Rui Wen, Jun Sakuma

llms fine-tuning safety

arXiv AI

Jun 11

Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models

arXiv:2606. 11409v1 Announce Type: cross Abstract: Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly.

By Malikeh Ehghaghi, Bogl\'arka Ecsedi, Marsha Chechik, Colin Raffel

llms reinforcement-learning multimodal benchmarks safety

arXiv AI

Jul 9

NonTextual Target Attack

arXiv:2510. 02999v5 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses.

By Xinzhe Huang, Wenjing Hu, Tianhang Zheng, Kedong Xiu, Hongsheng Hu, Xiaojun Jia, Di Wang, Zhan Qin, Kui Ren

llms benchmarks safety

One email a morning, machine-written

Related stories

A Few Steps Further: Why Defenses Against Malicious Finetuning Erode Under Continued Training

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models

NonTextual Target Attack