arXiv AI
Towards Merging-conditional Backdoor Unalignment against Large Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 23
Matching Ranks Over Probability Yields Truly Deep Safety Alignment
arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.
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.
Hugging Face Trending Papers
Jun 2
Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the trigger, leaving the defender at a structural disadvantage when unknown backdoors may exist in a model.
arXiv AI
Jun 3
Patcher: Post-Hoc Patching of Backdoored Large Language Models
arXiv:2606. 02995v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms.
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
Oct 3
Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation
The paper introduces NEEDLE, a training‑free technique for removing backdoors from large language models. After a trigger is identified, NEEDLE estimates a backdoor direction and a refusal subspace using activation vectors, then applies sequential weight orthogonalisation to suppress the backdoor while preserving refusal‑related representations. The method requires no clean reference model or original poisoned data and achieves the lowest attack success rate and minimal impact on model performance across multiple model families and attack types.