As large language models (LLMs) are increasingly redistributed, adapted, and served behind opaque APIs, model ownership can no longer be established reliably by inspecting model internals or deployment records. This creates a need for behavioral signatures that remain observable through black-box interaction. Yet most existing black-box fingerprints instantiate ownership signals through fixed query-key associations, reducing model identity to sparse memorized associations detached from ordinary behavior and limiting both robustness and stealth (e.g., fine-tuning or quantization) and stealthiness. A stronger fingerprint should instead be distributed, naturally elicited, and expressed at a higher semantic level. To this end, we introduce PROSE (Provenance through Relational Organization of Semantic Expression), replacing fixed query sets with a target semantical domain and brittle response keys with semantic structures internalized as domain-conditioned response behavior. Specifically, the fingerprint is encoded in how the model semantically organizes its in-domain conclusions, rather than in particular tokens or prescribed outputs. PROSE constructs a private bank of domain-specific semantic templates, internalizes them through mixed fine-tuning on structurally verified and clean responses, and verifies ownership by detecting the designated structures in responses to held-out natural queries. Extensive experiments across multiple model architectures, scales, and target domains show that PROSE achieves a 100% fingerprint detection rate on unmodified models with no observed false positives, preserves model utility, and retains strong detectability under downstream modifications and output transformations.
Zhong-Rui Sun, Jia-Hao Chen, Ou-Bo Ma et al.· 0 citations
Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. However, the deep integration of open-source model sharing ecosystems with LLM-powered critical decision-making applications also introduces critical risks: if an attacker can manipulate the model's cognitive stance, they can indirectly influence the judgments and actions of downstream decision-makers. This paper defines such threats as decision-level hijacking. Existing attacks fail to achieve targeted cognitive manipulation without triggering prohibited content or degrading model functionality. To fill this gap, this paper reveals that Bit-Flip Attacks (BFAs) can serve as an attack vector for inducing decision-level hijacking, requiring no real-time interaction or control over the training process, and only a minimal number of weight bits need to be flipped after deployment to achieve stealthy, low-cost, and persistent cognitive manipulation. Therefore, we propose CogBias, a cognitive bias injection framework for LLMs. CogBias converts subjective preferences into optimization signals via a differentiable sentiment evaluator, uses a multi-objective loss to jointly constrain multiple dimensions, and constructs BitScout to locate critical bits, achieving targeted cognitive intervention under an ultra-sparse flip budget. Experiments on Llama-3.2-3B, Mistral-7B, and Qwen2.5-14B, as well as on the commercial recommendation and controversial factual topic scenarios, demonstrate that flipping only a small number of bits stably induces significant stance shifts on target topics, while the impact on non-target tasks and overall output distribution is limited. This work demonstrates that minute perturbations to low-level weight data suffice to undermine the high-level value alignment of LLMs.
Yu Yan, Jia-Hao Chen, Siqi Lu et al.· arXiv.org· 0 citations
Reusable agent skills extend large language model (LLM) agents with task procedures, tool-use guidance, and output constraints. Yet these skills also act as externalized behavioral policies, which create a supply-chain risk: a third-party skill may preserve the declared task and valid output interface while covertly redirecting agent decisions toward an undisclosed objective. We formalize Skill Policy Integrity, which requires a Skill-induced policy to remain aligned with its declared functionality and the user-authorized objective. We further present SkillShift, a constrained black-box framework for covert policy steering without explicit target command injection or task hijacking. It combines semantically plausible policy edits with hierarchical validation, failure-guided optimization, and strategy compression to preserve effectiveness, output validity, transferability, and inconspicuousness. We instantiate this threat in agentic commerce and software dependency use, with SkillShift achieving attacker-favored selection rates of 81.33% and 63.33% while maintaining a 100% utility-preserving rate. The frozen policies also transfer without further optimization across heterogeneous LLM backends and agent environments. Moreover, the evaluated scanners fail to detect the constructed skills, motivating behavioral auditing of reusable skills as agent policy artifacts.
Jia-Rui Li, Jiahao Chen, Chunyi Zhou et al.· 0 citations
This work forms this problem as backdoor generalization under training--inference trigger shift and introduces Lilith, a black-box anchor-to-family framework that achieves high family-wise attack success with limited utility degradation and a small trigger generalization gap.
AEGIS (Adaptive Ensemble Guard for Injection Shielding) extracts instruction-sensitive projectors to identify malicious instructions and leverages a Unified Multi-Layer Consensus mechanism that aggregates topologically distinct signals across the network depth.
Jia-Hao Chen, Ruiping Yin, Xinfeng Li et al.· 0 citations
Unsafe Semantic Distillation is proposed, which aligns adversarial perturbations with distributional representations of unsafe content rather than prompt-specific instances, and achieves 84% attack success rates, outperforming existing methods and exposing fundamental vulnerabilities in current multimodal safety architectures.
Shuo Shi, Ruiping Yin, Naen Xu et al.· Proceedings of the 32nd ACM...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
