Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g. thoughts and feelings) that are not accessible to external observers. Do LLMs have this introspective capability of privileged access? If they do, this would show that LLMs can acquire knowledge not contained in or inferable from training data. We investigate LLMs predicting properties of their own behavior in hypothetical situations. If a model M1 has this capability, it should outperform a different model M2 in predicting M1's behavior—even if M2 is trained on M1's ground-truth behavior. The idea is that M1 has privileged access to its own behavioral tendencies, and this enables it to predict itself better than M2 (even if M2 is generally stronger). In experiments with GPT-4, GPT-4o, and Llama-3 models, we find that the model M1 outperforms M2 in predicting itself, providing evidence for privileged access. Further experiments and ablations provide additional evidence. Our results show that LLMs can offer reliable self-information independent of external data in certain domains. By demonstrating this, we pave the way for further work on introspection in more practical domains, which would have significant implications for model transparency and explainability. However, while we successfully show introspective capabilities in simple tasks, we are unsuccessful on more complex tasks or those requiring out-of-distribution generalization.

The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways. In this work, we focus on a popular class of vision-language models (VLMs) that generate text outputs conditioned on visual and textual inputs. We conducted a large-scale empirical study to assess the transferability of gradient-based universal image "jailbreaks" using a diverse set of over 40 open-parameter VLMs, including 18 new VLMs that we publicly release. Overall, we find that transferable gradient-based image jailbreaks are extremely difficult to obtain. When an image jailbreak is optimized against a single VLM or against an ensemble of VLMs, the jailbreak successfully jailbreaks the attacked VLM(s), but exhibits little-to-no transfer to any other VLMs; transfer is not affected by whether the attacked and target VLMs possess matching vision backbones or language models, whether the language model underwent instruction-following and/or safety-alignment training, or many other factors. Only two settings display partially successful transfer: between identically-pretrained and identically-initialized VLMs with slightly different VLM training data, and between different training checkpoints of a single VLM. Leveraging these results, we then demonstrate that transfer can be significantly improved against a specific target VLM by attacking larger ensembles of "highly-similar" VLMs. These results stand in stark contrast to existing evidence of universal and transferable text jailbreaks against language models and transferable adversarial attacks against image classifiers, suggesting that VLMs may be more robust to gradient-based transfer attacks.

As large language models (LLMs) grow more powerful, they also become more difficult to trust. They could be either aligned with human intentions, or exhibit "subversive misalignment" -- introducing subtle errors that bypass safety checks. Although individual errors may not immediately cause harm, each increases the risk of an eventual safety failure. With this uncertainty, model deployment often grapples with the tradeoff between ensuring safety and harnessing the capabilities of untrusted models. In this work, we introduce the ``Diffuse Risk Management'' problem, aiming to balance the average-case safety and usefulness in the deployment of untrusted models over a large sequence of tasks. We approach this problem by developing a two-level framework: the single-task level (micro-protocol) and the whole-scenario level (macro-protocol). At the single-task level, we develop various \textit{micro}-protocols that use a less capable, but extensively tested (trusted) model to harness and monitor the untrusted model. At the whole-scenario level, we find an optimal \textit{macro}-protocol that uses an adaptive estimate of the untrusted model's risk to choose between micro-protocols. To evaluate the robustness of our method, we follow \textit{control evaluations} in a code generation testbed, which involves a red team attempting to generate subtly backdoored code with an LLM whose deployment is safeguarded by a blue team. Experiment results show that our approach retains 99.6\% usefulness of the untrusted model while ensuring near-perfect safety, significantly outperforming existing deployment methods. Our approach also demonstrates robustness when the trusted and untrusted models have a large capability gap. Our findings demonstrate the promise of managing diffuse risks in the deployment of increasingly capable but untrusted LLMs.

Large language models often possess latent capabilities that lie dormant unless explicitly elicited, or surfaced, through fine-tuning or prompt engineering. Predicting, assessing, and understanding these latent capabilities pose significant challenges in the development of effective, safe AI systems. In this work, we recast elicitation as an information-constrained fine-tuning problem and empirically characterize upper bounds on the minimal number of parameters needed to achieve specific task performances. We find that training as few as 10–100 randomly chosen parameters—several orders of magnitude fewer than state-of-the-art parameter-efficient methods—can recover up to 50\% of the performance gap between pretrained-only and full fine-tuned models, and 1,000s to 10,000s of parameters can recover 95\% of this performance gap. We show that a logistic curve fits the relationship between the number of trained parameters and model performance gap recovery. This scaling generalizes across task formats and domains, as well as model sizes and families, extending to reasoning models and remaining robust to increases in inference compute. To help explain this behavior, we consider a simplified picture of elicitation via fine-tuning where each trainable parameter serves as an encoding mechanism for accessing task-specific knowledge. We observe a relationship between the number of trained parameters and how efficiently relevant model capabilities can be accessed and elicited, offering a potential route to distinguish elicitation from teaching.

We introduce Best-of-N (BoN) Jailbreaking, a simple black-box algorithm that jailbreaks frontier AI systems across modalities. BoN Jailbreaking works by repeatedly sampling variations of a prompt with a combination of augmentations---such as random shuffling or capitalization for textual prompts---until a harmful response is elicited. We find that BoN Jailbreaking achieves high attack success rates (ASRs) on closed-source language models, such as 89% on GPT-4o and 78% on Claude 3.5 Sonnet when sampling 10,000 augmented prompts. Further, it is similarly effective at circumventing state-of-the-art open-source defenses like circuit breakers and reasoning models like o1. BoN also seamlessly extends to other modalities: it jailbreaks vision language models (VLMs) such as GPT-4o and audio language models (ALMs) like Gemini 1.5 Pro, using modality-specific augmentations. BoN reliably improves when we sample more augmented prompts. Across all modalities, ASR, as a function of the number of samples (N), empirically follows power-law-like behavior for many orders of magnitude. BoN Jailbreaking can also be composed with other black-box algorithms for even more effective attacks---combining BoN with an optimized prefix attack achieves up to a 35% increase in ASR. Overall, our work indicates that, despite their capability, language models are sensitive to seemingly innocuous changes to inputs, which attackers can exploit across modalities.