Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
Authors: Tobias Braun, Jonas Henry Grebe, Hossein Shakibania et al.
Summary
arXiv:2605. 19227v1 Announce Type: new Abstract: Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass.
Relevance
Read next because Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, word, token, line, rate, without, propagate, model. Source: arxiv cs.CR (Cryptography and Security).
Abstract
arXiv:2605.19227v1 Announce Type: new Abstract: Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocabulary simplify the training pipeline and facilitate flexible multimodal generation, yet might introduce new vulnerabilities. In particular, we are the first to show that this unified architecture enables multimodal backdoor attacks, where a trigger can propagate malicious effects across multiple output modalities. Specifically, we present the Token by Token Backdoor Attack (ToBAC), the first backdoor attack targeting UAMs, exploring both data-based and model-based poisoning strategies. We demonstrate that innocuous characters or even common words can be transformed into triggers that elicit harmful behavior in autoregressive image generation. ToBAC can jointly manipulate visual outputs and accompanying text, increasing the perceived authenticity of fabricated content. With model access, ToBAC enables attacks on the unified Liquid model in which a subtle word (e.g., ``cool'') induces modality-aligned brand promotion or ideological influence in 55% of generations. Without model access, ToBAC can be induced through data poisoning, achieving an average success rate of 63.1% against JanusPro.