arXiv Machine Learning
A Few Steps Further: Why Defenses Against Malicious Finetuning Erode Under Continued Training
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
6d ago
Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks
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.
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.
arXiv AI
Aug 6
Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning
arXiv:2608. 05045v1 Announce Type: cross Abstract: Released aligned large language models remain vulnerable to malicious downstream finetuning.
arXiv Machine Learning
Jul 30
ToxScreen: Detecting Whether an LLM Has Been Poisoned
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
arXiv Machine Learning
Jul 28
When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs
arXiv:2607. 24392v1 Announce Type: cross Abstract: Jailbreak defenses are essential for protecting large language models (LLMs), but they can also introduce secondary costs that weaken model utility.
arXiv Computation and Language
Sep 16
Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion
The paper introduces the SAST-IR framework to evaluate large language models’ robustness against persuasion attacks in a memory‑less setting, revealing a flaw called "Refusal Inertia" that masks true vulnerability. Using the CP‑Agent and a custom CounterFact‑Strict dataset, the authors demonstrate that simple, diverse attack strategies achieve a 96% success rate, while complex attacks often trigger defensive compliance. The study highlights severe brittleness in current state‑of‑the‑art models when deprived of conversation history.