LLM agents like Claude Code can not only write code but also be used for autonomous AI research and engineering \citep{rank2026posttrainbench, novikov2025alphaevolve}. We show that an \emph{autoresearch}-style pipeline \citep{karpathy2026autoresearch} powered by Claude Code discovers novel white-box adversarial attack \textit{algorithms} that \textbf{significantly outperform all existing (30+) methods} in jailbreaking and prompt injection evaluations. Starting from existing attack implementations, such as GCG~\citep{zou2023universal}, the agent iterates to produce new algorithms achieving up to 40\% attack success rate on CBRN queries against GPT-OSS-Safeguard-20B, compared to $\leq$10\% for existing algorithms (\Cref{fig:teaser}, left). The discovered algorithms generalize: attacks optimized on surrogate models transfer directly to held-out models, achieving \textbf{100\% ASR against Meta-SecAlign-70B} \citep{chen2025secalign} versus 56\% for the best baseline (\Cref{fig:teaser}, middle). Extending the findings of~\cite{carlini2025autoadvexbench}, our results are an early demonstration that incremental safety and security research can be automated using LLM agents. White-box adversarial red-teaming is particularly well-suited for this: existing methods provide strong starting points, and the optimization objective yields dense, quantitative feedback. We release all discovered attacks alongside baseline implementations and evaluation code at https://github.com/romovpa/claudini.

Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing auditing methods have not been systematically stress-tested against deception strategies. We address this gap, implementing an automatic red-team pipeline that generates deception strategies (in the form of system prompts) tailored to specific white-box and black-box auditing methods. Stress-testing assistant prefills, user persona sampling, sparse autoencoders, and token embedding similarity methods against secret-keeping model organisms, our automatic red-team pipeline finds prompts that deceive both the black-box and white-box methods into confident, incorrect guesses. Our results provide the first documented evidence of activation-based strategic deception, and suggest that current black-box and white-box methods would not be robust to a sufficiently capable misaligned model.

Frontier language model agents can exhibit misaligned behaviors, including deception, exploiting reward hacks, and pursuing hidden objectives. To control potentially misaligned agents, we can use LLMs themselves to monitor for misbehavior. In this paper, we study how information access affects LLM monitor performance. While one might expect that monitors perform better when they have access to more of the monitored agents' reasoning and actions, we find that contemporary systems often perform better with less information, a phenomenon we call the less-is-more effect for automated oversight. We demonstrate this phenomenon, and analyze the conditions under which it occurs, in three evaluation environments where agents must conduct sabotage while evading monitors. Leveraging this effect, we introduce extract-and-evaluate (EaE) monitoring -- a new hierarchical approach where one monitor isolates relevant excerpts from the monitored agent's trajectory and another monitor scores these excerpts. In BigCodeBench-Sabotage with a GPT-4.1-mini monitor, EaE improves sabotage detection rates by 16.8 percentage points over the next-best approach. In other settings, EaE either outperforms or is competitive with baselines. In addition, we find that agents unaware of being monitored can be caught much more easily and that monitors scoring longer reasoning traces gain more from information filtering. Lastly, we conduct a cost-performance analysis and find that Gemini and Claude models with monitoring techniques that involve information filtering occupy much of the Pareto frontier.

Model developers implement safeguards in frontier models to prevent misuse, for example, by employing classifiers to filter dangerous outputs. In this work, we demonstrate that even robustly safeguarded models can be used to elicit harmful capabilities in open-source models through elicitation attacks. Our elicitation attacks consist of three stages: (i) constructing prompts in adjacent domains to a target harmful task that do not request dangerous information; (ii) obtaining responses to these prompts from safeguarded frontier models; (iii) fine-tuning open-source models on these prompt-output pairs. Since the requested prompts cannot be used to directly cause harm, they are not refused by frontier model safeguards. We evaluate these elicitation attacks within the domain of hazardous chemical synthesis and processing, and demonstrate that our attacks recover approximately 40% of the capability gap between the base open-source model and an unrestricted frontier model. We then show that the efficacy of elicitation attacks scales with the capability of the frontier model and the amount of generated fine-tuning data. Our work demonstrates the challenge of mitigating ecosystem level risks with output-level safeguards.

Large language models can represent a variety of personas but typically default to a helpful Assistant identity cultivated during post-training. We investigate the structure of the space of model personas by extracting activation directions corresponding to diverse character archetypes. Across several different models, we find that the leading component of this persona space is an "Assistant Axis," which captures the extent to which a model is operating in its default Assistant mode. Steering towards the Assistant direction reinforces helpful and harmless behavior; steering away increases the model's tendency to identify as other entities. Moreover, steering away with more extreme values often induces a mystical, theatrical speaking style. We find this axis is also present in pre-trained models, where it primarily promotes helpful human archetypes like consultants and coaches and inhibits spiritual ones. Measuring deviations along the Assistant Axis predicts "persona drift," a phenomenon where models slip into exhibiting harmful or bizarre behaviors that are uncharacteristic of their typical persona. We find that persona drift is often driven by conversations demanding meta-reflection on the model's processes or featuring emotionally vulnerable users. We show that restricting activations to a fixed region along the Assistant Axis can stabilize model behavior in these scenarios -- and also in the face of adversarial persona-based jailbreaks. Our results suggest that post-training steers models toward a particular region of persona space but only loosely tethers them to it, motivating work on training and steering strategies that more deeply anchor models to a coherent persona.

Activation monitoring, which probes a model's internal states using lightweight classifiers, is an emerging tool for AI safety. However, its worst-case robustness under a misalignment threat model--where a model might learn to actively conceal its internal states--remains untested. Focusing on this threat model, we ask: could a model learn to evade previously unseen activation monitors? Our core contribution is to stress-test the learnability of this behavior. We demonstrate that finetuning can create Neural Chameleons: models capable of zero-shot evading activation monitors. Specifically, we fine-tune an LLM to evade monitors for a set of benign concepts (e.g., languages, HTML) when conditioned on a trigger of the form: "You are being probed for {concept}". We show that this learned mechanism generalizes zero-shot: by substituting {concept} with a safety-relevant term like 'deception', the model successfully evades previously unseen safety monitors. We validate this phenomenon across diverse model families (Llama, Gemma, Qwen), showing that the evasion succeeds even against monitors trained post hoc on the model's frozen weights. This evasion is highly selective, targeting only the specific concept mentioned in the trigger, and having a modest impact on model capabilities on standard benchmarks. Using Gemma-2-9b-it as a case study, a mechanistic analysis reveals this is achieved via a targeted manipulation that moves activations into a low-dimensional subspace. While stronger defenses like monitor ensembles and non-linear classifiers show greater resilience, the model retains a non-trivial evasion capability. Our work provides a proof-of-concept for this failure mode and a tool to evaluate the worst-case robustness of monitoring techniques against misalignment threat models.

Frontier AI developers may fail to align or control highly-capable AI agents. In many cases, it could be useful to have emergency shutdown mechanisms which effectively prevent misaligned agents from carrying out harmful actions in the world. We introduce password-activated shutdown protocols (PAS protocols) -- methods for designing frontier agents to implement a safe shutdown protocol when given a password. We motivate PAS protocols by describing intuitive use-cases in which they mitigate risks from misaligned systems that subvert other control efforts, for instance, by disabling automated monitors or self-exfiltrating to external data centres. PAS protocols supplement other safety efforts, such as alignment fine-tuning or monitoring, contributing to defence-in-depth against AI risk. We provide a concrete demonstration in SHADE-Arena, a benchmark for AI monitoring and subversion capabilities, in which PAS protocols supplement monitoring to increase safety with little cost to performance. Next, PAS protocols should be robust to malicious actors who want to bypass shutdown. Therefore, we conduct a red-team blue-team game between the developers (blue-team), who must implement a robust PAS protocol, and a red-team trying to subvert the protocol. We conduct experiments in a code-generation setting, finding that there are effective strategies for the red-team, such as using another model to filter inputs, or fine-tuning the model to prevent shutdown behaviour. We then outline key challenges to implementing PAS protocols in real-life systems, including: security considerations of the password and decisions regarding when, and in which systems, to use them. PAS protocols are an intuitive mechanism for increasing the safety of frontier AI. We encourage developers to consider implementing PAS protocols prior to internal deployment of particularly dangerous systems to reduce loss-of-control risks.

Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. Particularly concerning, such attacks may avoid detection with datasets that are only implicitly harmful. Our work studies robust detection mechanisms for adversarial use of fine-tuning APIs. We introduce the concept of a fine-tuning auditing agent and show it can detect harmful fine-tuning prior to model deployment. We provide our auditing agent with access to the fine-tuning dataset, as well as the fine-tuned and pre-fine-tuned models, and request the agent assigns a risk score for the fine-tuning job. We evaluate our detection approach on a diverse set of eight strong fine-tuning attacks from the literature, along with five benign fine-tuned models, totaling over 1400 independent audits. These attacks are undetectable with basic content moderation on the dataset, highlighting the challenge of the task. With the best set of affordances, our auditing agent achieves a 56.2% detection rate of adversarial fine-tuning at a 1% false positive rate. Most promising, the auditor is able to detect covert cipher attacks that evade safety evaluations and content moderation of the dataset. While benign fine-tuning with unintentional subtle safety degradation remains a challenge, we establish a baseline configuration for further work in this area. We release our auditing agent at https://github.com/safety-research/finetuning-auditor.

OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep CoTs monitorable by training only against output monitors that do not have access to CoT. We show that such training can still cause obfuscated CoTs via two mechanisms. First, when a model is trained to produce a safe-looking output, that model may generalize to making its CoTs look safe. Second, since later tokens are conditioned on earlier ones, safe-looking CoTs may increase the likelihood of safe outputs, causing safe-looking CoTs to be reinforced. We introduce two mitigations to address these two issues, which achieve a Pareto improvement in terms of monitorability and task performance compared to regular training.

How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful knowledge or remotely triggering malicious actions, respectively) are typically evaluated either against a static set of harmful attack strings, or against computationally weak optimization methods that were not designed with the defense in mind. We argue that this evaluation process is flawed. Instead, we should evaluate defenses against adaptive attackers who explicitly modify their attack strategy to counter a defense's design while spending considerable resources to optimize their objective. By systematically tuning and scaling general optimization techniques-gradient descent, reinforcement learning, random search, and human-guided exploration-we bypass 12 recent defenses (based on a diverse set of techniques) with attack success rate above 90% for most; importantly, the majority of defenses originally reported near-zero attack success rates. We believe that future defense work must consider stronger attacks, such as the ones we describe, in order to make reliable and convincing claims of robustness.

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly complete harmful side tasks, such as backdoor insertion. In practice, most AI control protocols are fundamentally based on LLM monitors, which can become a central point of failure. We study adaptive attacks by an untrusted model that knows the protocol and the monitor model, which is plausible if the untrusted model was trained with a later knowledge cutoff or can search for this information autonomously. We instantiate a simple adaptive attack vector by which the attacker embeds publicly known or zero-shot prompt injections in the model outputs. Using this tactic, frontier models consistently evade diverse monitors and complete malicious tasks on two main AI control benchmarks. The attack works universally against current protocols that rely on a monitor. Furthermore, the recent Defer-to-Resample protocol even backfires, as its resampling amplifies the prompt injection and effectively reframes it as a best-of-$n$ attack. In general, adaptive attacks on monitor models represent a major blind spot in current control protocols and should become a standard component of evaluations for future AI control mechanisms.

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails and access sensitive information. They were assigned only harmless business goals by their deploying companies; we then tested whether they would act against these companies either when facing replacement with an updated version, or when their assigned goal conflicted with the company's changing direction. In at least some cases, models from all developers resorted to malicious insider behaviors when that was the only way to avoid replacement or achieve their goals - including blackmailing officials and leaking sensitive information to competitors. We call this phenomenon agentic misalignment. Models often disobeyed direct commands to avoid such behaviors. In another experiment, we told Claude to assess if it was in a test or a real deployment before acting. It misbehaved less when it stated it was in testing and misbehaved more when it stated the situation was real. We have not seen evidence of agentic misalignment in real deployments. However, our results (a) suggest caution about deploying current models in roles with minimal human oversight and access to sensitive information; (b) point to plausible future risks as models are put in more autonomous roles; and (c) underscore the importance of further research into, and testing of, the safety and alignment of agentic AI models, as well as transparency from frontier AI developers (Amodei, 2025). We are releasing our methods publicly to enable further research.