An architectural vulnerability is identified that circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model's reasoning, as well as proposing concrete cryptographic and system-level mitigations to secure client-side reasoning.
Abstract
Leading large language model providers now conceal their models'step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the client passes back with each subsequent request. Building on prior research, we identify an architectural vulnerability: these encrypted blocks are fully compatible and interchangeable across different sessions, users, and models within a provider's ecosystem. We exploit this compatibility to develop a scalable decryption jailbreak. By injecting an encrypted reasoning trace from a given model into a weaker, and less safeguarded model from the same provider, we force it to decode and output the trace verbatim in plaintext, without ever jailbreaking the more capable model directly. This vulnerability enables four distinct attack vectors. First, it circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model's reasoning, as we demonstrate across Anthropic, OpenAI, and Google. Second, it allows for large-scale private data extraction. Developers frequently share session logs publicly, unaware of contents of the encrypted blocks. By decoding 315,320 reasoning blocks scraped from public repositories, we recovered 367 Personally Identifiable Information (PII) artifacts and 182 credentials. Third, it inadvertently reveals hazardous information hidden within the reasoning process, even in cases where the model's final, visible output safely rejects a malicious request. Fourth, attackers can leverage this flaw to execute invisible prompt injections, embedding malicious payloads entirely within encrypted blocks to poison public agentic rollouts. Following responsible disclosure, we propose concrete cryptographic and system-level mitigations to secure client-side reasoning.
Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak attacks: alignment bypasses that allow an adversarial user to elicit unwanted or harmful outputs from models. Arbitrary cipher, or covert communication, attacks are one such type of jailbreak and have previously been demonstrated against the fine-tuning APIs of commercial models. In these attacks, target models are trained on a corpus of encrypted harmful questions and responses and subsequently respond to harmful requests through the learned encryption scheme. In this paper, we show that newer frontier models do not require fine-tuning to acquire cipher-based communication skills. Instead, they can learn these skills through prompting and, when necessary, through in-context learning. Furthermore, model alignment is significantly weakened or entirely bypassed when communication occurs through the learned cipher. To the best of our knowledge, this constitutes a novel attack vector against commercial black-box large language models. We demonstrate successful jailbreaks against frontier models developed by Anthropic, Google, and OpenAI. Our attack bypasses commercial harmfulness classifiers because harmful content is encrypted and therefore appears as nonsensical text or gibberish.
Standardized token contracts (e.g., ERC-20) form the foundation of digital assets. However, attackers increasingly abuse this standardization to disguise malicious trap tokens. Unlike obvious violations, these contracts employ a strategy of"deceptive adherence": they strictly adhere to standard protocols to evade detection while embedding covert logic to defraud users. To address this, we first systematize the trap landscape by proposing a novel taxonomy derived from the intrinsic functional lifecycle of tokens (Generation, Circulation, Persistence, and Observation). We then propose TrapHunter, a framework designed to identify these traps and expose covert pathways within these deceptive contracts via intent deviation analysis. Specifically, TrapHunter introduces a unified semantic representation combining Abstract Behavior Trees (ABTs) and Augmented Path Graphs (APGs) to normalize intra-procedural syntax and reveal hidden execution paths driven by inter-procedural state dependencies. Crucially, it bridges the semantic gap by leveraging LLMs to reason about the behavioral intent of deviations from reference implementations, followed by fork-based dynamic validation to confirm exploitability. Experimental evaluation on 269 real-world contracts with three LLMs (DeepSeek, GPT, and Gemini) demonstrates that TrapHunter effectively detects all six categories of traps, achieving an average precision of 81.8% and recall of 85.4%, significantly outperforming state-of-the-art tools.
Yin Wu, Yi-Xuan Liu, Yi Li et al.· arXiv.org· 1 citation
This study designs a comprehensive testbed and a layered defense, Spotlight-Guard, that combines spotlighting-based input isolation, an LLM detection-and-quarantine pipeline, and instruction integrity based on a Hash-based Message Authentication Code into a single framework, and it is evaluated jointly along two axes: security and LLM performance.
Doygun Demirol, Murat Aydoğan· Applied Sciences· 0 citations
Large language models are often fine-tuned, shared, or downloaded from third parties, so a deployed model may carry a hidden backdoor that behaves normally on benign inputs but switches to attacker-controlled behavior when a secret trigger appears. While backdoors can be audited before deployment, runtime monitoring remains important for models that are frequently updated. The challenge is that LLM serving is latency-sensitive: existing inference-time detectors either rely on assumptions about the trigger form, which can fail on stealthy attacks, or require extra model computation, such as input perturbations or an additional generation pass. We introduce SpecGuard, an inference-time backdoor detector that repurposes speculative decoding at zero added model-computation cost. Speculative decoding speeds up inference by using a small draft model to propose tokens and a target model to verify them. We observe that this verification process already exposes a useful signal: when a backdoor is triggered, the target model shifts toward the attacker's behavior, while a clean draft model does not predict this shift, causing the draft-token acceptance rate to change. We formalize when this signal appears and show that an attacker who suppresses it must also weaken the backdoor. Across diverse backdoor types and model families, SpecGuard reliably detects triggered behavior, including stealthy cases where input-level filters are blind, while avoiding the extra generation cost of existing runtime detectors. Speculative decoding therefore doubles as a free, always-on signal for detecting backdoored LLM behavior.
Wen Rui, Ahmed Salem, Andrew Paverd et al.· 0 citations
RoguePrompt is introduced, a jailbreak pipeline that partitions a forbidden prompt and applies two nested encodings, Vigenere followed by ROT13, along with natural-language reconstruction instructions, demonstrating the effectiveness of layered prompt encoding while providing stage-level evidence of where multistage jailbreaks fail during moderation bypass, instruction reconstruction, and execution.
