Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

Computer Science > Artificial Intelligence [Submitted on 6 Jun 2026] Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs Omar Mahmoud, Aly M. Kassem, Thommen George Karimpanal, Buddhika Laknath Semage, Negar Rostamzadeh, Golnoosh Farnadi, Santu Rana Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific triggers or behaviors. We show this view is incomplete. Across diverse backdoor behaviors, we identify a shared latent mechanism that can be detected, causally controlled, and suppressed. Using sparse autoencoders (SAEs) on residual-stream activations, we find a small set of latent features consistently activated across jailbreaking, refusal manipulation, password-locking, bias induction, sentiment misclassification, and country-conditioned harmful advice. These features generalize across Qwen3, Gemma~3, and Llama~3.1 models from 4B to 32B parameters, and across both fine-tuning and weight-editing attacks. Through bidirectional activation steering, we show these features are causal: suppressing them reduces attack success, while amplifying them induces target behaviors on clean prompts. We further train lightweight SAE-feature classifiers that generalize zero-shot to unseen backdoors and outperform residual-stream and weight-diffing baselines. Finally, we introduce Concept Ablation Fine-Tuning (CAFT), which suppresses backdoor formation by ablating the shared latent subspace during training. Together, our results suggest that many backdoors rely on a transferable latent mechanism, enabling unified detection and mitigation. Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2606.07963 [cs.AI]   (or arXiv:2606.07963v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.07963 Focus to learn more Submission history From: Omar Mohamed Ahmed Mahmoud [view email] [v1] Sat, 6 Jun 2026 03:41:44 UTC (1,268 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)