← Back to all news
arXiv AI By Danny Wood, James Stringer

Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures

Read the original on arXiv AI →

The paper investigates the threat of stegomalware—malicious payloads hidden in large language model weights—and explores permutation symmetry as a defense. It demonstrates that carefully chosen permutations can neutralize stegomalware across all weights, unlike prior methods that left many weights untouched. Conversely, the same symmetry can be exploited to embed malware losslessly, without retraining or payload-specific extraction scripts, while only minimally affecting model performance.

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 AI.

Related stories

arXiv Machine Learning
4d ago

All-in-One: A Composable Attack on LLM Transformations

The paper introduces a unified attack framework that can simultaneously target multiple large language model (LLM) transformations such as quantization, pruning, and model merging. By treating each transformation as a weight perturbation, the authors jointly train a model to perform benignly before transformation and maliciously after any one of the transformations is applied. Experiments across various attack scenarios and model families show high success rates, illustrating that a single adversarial model can exploit diverse deployment-time transformations.

By Xiaohua Zhan, Kazuki Egashira, Robin Staab, Mark Vero, Martin Vechev
llmsefficiencysafety
More like this →
arXiv Machine Learning
Oct 8

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.

By Kevin Kuo, Virginia Smith, Chhavi Yadav
llmsfine-tuningbenchmarkssafety
More like this →
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
llmsfine-tuningbenchmarkssafety
More like this →
arXiv Machine Learning
Jun 3

RogueMerge: Robust and Unified Attacks against LLM Model Merging

arXiv:2606. 03344v1 Announce Type: cross Abstract: Model merging composes specialized capabilities into a single LLM by aggregating task vectors sourced from unverified public platforms, exposing a critical supply-chain attack surface: Because any malicious behavior can be encoded into a task vector, and merging grants third-party vectors direct write access to model weights, an attacker-provided task vector can enable or amplify diverse downstream threats.

By Jinghuai Zhang, Yetian He, Kunlin Cai, Han Zhao, Fnu Suya, Yuan Tian
llms
More like this →
Hugging Face Trending Papers
Jun 2

RogueMerge: Robust and Unified Attacks against LLM Model Merging

Model merging composes specialized capabilities into a single LLM by aggregating task vectors sourced from unverified public platforms, exposing a critical supply-chain attack surface: Because any malicious behavior can be encoded into a task vector, and merging grants third-party vectors direct write access to model weights, an attacker-provided task vector can enable or amplify diverse downstream threats. Prior work studies only backdoor attacks against model merging for classifiers using static arithmetic heuristics, which fail to effectively handle diverse attacks on generative LLMs for three reasons.

llms
More like this →