AI systems sometimes exhibit harmful unintended behaviors post-deployment. This is often despite extensive diagnostics and debugging by developers. Minimizing risks from models is challenging because the attack surface is so large. It is not tractable to exhaustively search for inputs that may cause a model to fail. Red-teaming and adversarial training (AT) are commonly used to make AI systems more robust. However, they have not been sufficient to avoid many real-world failure modes that differ from the ones adversarially trained on. In this work, we utilize latent adversarial training (LAT) to defend against vulnerabilities without generating inputs that elicit them. LAT leverages the compressed, abstract, and structured latent representations of concepts that the network actually uses for prediction. We use LAT to remove trojans and defend against held-out classes of adversarial attacks. We show in image classification, text classification, and text generation tasks that LAT usually improves both robustness and performance on clean data relative to AT. This suggests that LAT can be a promising tool for defending against failure modes that are not explicitly identified by developers.
Machine unlearning can be useful for removing harmful capabilities and memorized text from large language models (LLMs), but there are not yet standardized methods for rigorously evaluating it. In this paper, we first survey techniques and limitations of existing unlearning evaluations. Second, we apply a comprehensive set of tests for the robustness and competitiveness of unlearning in the "Who's Harry Potter" (WHP) model from Eldan and Russinovich (2023). While WHP's unlearning generalizes well when evaluated with the "Familiarity" metric from Eldan and Russinovich, we find i) higher-than-baseline amounts of knowledge can reliably be extracted, ii) WHP performs on par with the original model on Harry Potter Q&A tasks, iii) it represents latent knowledge comparably to the original model, and iv) there is collateral unlearning in related domains. Overall, our results highlight the importance of comprehensive unlearning evaluation that avoids ad-hoc metrics.
We explore machine unlearning (MU) in the domain of large language models (LLMs), referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities, while maintaining the integrity of essential knowledge generation and not affecting causally unrelated information. We envision LLM unlearning becoming a pivotal element in the life-cycle management of LLMs, potentially standing as an essential foundation for developing generative AI that is not only safe, secure, and trustworthy, but also resource-efficient without the need of full retraining. We navigate the unlearning landscape in LLMs from conceptual formulation, methodologies, metrics, and applications. In particular, we highlight the often-overlooked aspects of existing LLM unlearning research, e.g., unlearning scope, data-model interaction, and multifaceted efficacy assessment. We also draw connections between LLM unlearning and related areas such as model editing, influence functions, model explanation, adversarial training, and reinforcement learning. Furthermore, we outline an effective assessment framework for LLM unlearning and explore its applications in copyright and privacy safeguards and sociotechnical harm reduction.
External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depends on the degree of system access granted to auditors. Recent audits of state-of-the-art AI systems have primarily relied on black-box access, in which auditors can only query the system and observe its outputs. However, white-box access to the system's inner workings (e.g., weights, activations, gradients) allows an auditor to perform stronger attacks, more thoroughly interpret models, and conduct fine-tuning. Meanwhile, outside-the-box access to its training and deployment information (e.g., methodology, code, documentation, hyperparameters, data, deployment details, findings from internal evaluations) allows for auditors to scrutinize the development process and design more targeted evaluations. In this paper, we examine the limitations of black-box audits and the advantages of white- and outside-the-box audits. We also discuss technical, physical, and legal safeguards for performing these audits with minimal security risks. Given that different forms of access can lead to very different levels of evaluation, we conclude that (1) transparency regarding the access and methods used by auditors is necessary to properly interpret audit results, and (2) white- and outside-the-box access allow for substantially more scrutiny than black-box access alone.
Neural language models (LMs) can be used to evaluate the truth of factual statements in two ways: they can be either queried for statement probabilities, or probed for internal representations of truthfulness. Past work has found that these two procedures sometimes disagree, and that probes tend to be more accurate than LM outputs. This has led some researchers to conclude that LMs "lie" or otherwise encode non-cooperative communicative intents. Is this an accurate description of today's LMs, or can query-probe disagreement arise in other ways? We identify three different classes of disagreement, which we term confabulation, deception, and heterogeneity. In many cases, the superiority of probes is simply attributable to better calibration on uncertain answers rather than a greater fraction of correct, high-confidence answers. In some cases, queries and probes perform better on different subsets of inputs, and accuracy can further be improved by ensembling the two. Code is available at github.com/lingo-mit/lm-truthfulness.
Despite efforts to align large language models to produce harmless responses, they are still vulnerable to jailbreak prompts that elicit unrestricted behaviour. In this work, we investigate persona modulation as a black-box jailbreaking method to steer a target model to take on personalities that are willing to comply with harmful instructions. Rather than manually crafting prompts for each persona, we automate the generation of jailbreaks using a language model assistant. We demonstrate a range of harmful completions made possible by persona modulation, including detailed instructions for synthesising methamphetamine, building a bomb, and laundering money. These automated attacks achieve a harmful completion rate of 42.5% in GPT-4, which is 185 times larger than before modulation (0.23%). These prompts also transfer to Claude 2 and Vicuna with harmful completion rates of 61.0% and 35.9%, respectively. Our work reveals yet another vulnerability in commercial large language models and highlights the need for more comprehensive safeguards.
Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of-the-art large language models (LLMs). Despite this popularity, there has been relatively little public work systematizing its flaws. In this paper, we (1) survey open problems and fundamental limitations of RLHF and related methods; (2) overview techniques to understand, improve, and complement RLHF in practice; and (3) propose auditing and disclosure standards to improve societal oversight of RLHF systems. Our work emphasizes the limitations of RLHF and highlights the importance of a multi-faceted approach to the development of safer AI systems.
Modern diffusion models have set the state-of-the-art in AI image generation. Their success is due, in part, to training on Internet-scale data which often includes copyrighted work. This prompts questions about the extent to which these models learn from, imitate, or copy the work of human artists. This work suggests that tying copyright liability to the capabilities of the model may be useful given the evolving ecosystem of generative models. Specifically, much of the legal analysis of copyright and generative systems focuses on the use of protected data for training. As a result, the connections between data, training, and the system are often obscured. In our approach, we consider simple image classification techniques to measure a model's ability to imitate specific artists. Specifically, we use Contrastive Language-Image Pretrained (CLIP) encoders to classify images in a zero-shot fashion. Our process first prompts a model to imitate a specific artist. Then, we test whether CLIP can be used to reclassify the artist (or the artist's work) from the imitation. If these tests match the imitation back to the original artist, this suggests the model can imitate that artist's expression. Our approach is simple and quantitative. Furthermore, it uses standard techniques and does not require additional training. We demonstrate our approach with an audit of Stable Diffusion's capacity to imitate 70 professional digital artists with copyrighted work online. When Stable Diffusion is prompted to imitate an artist from this set, we find that the artist can be identified from the imitation with an average accuracy of 81.0%. Finally, we also show that a sample of the artist's work can be matched to these imitation images with a high degree of statistical reliability. Overall, these results suggest that Stable Diffusion is broadly successful at imitating individual human artists.
Deploying Large language models (LLMs) can pose hazards from harmful outputs such as toxic or dishonest speech. Prior work has introduced tools that elicit harmful outputs in order to identify and mitigate these risks. While this is a valuable step toward securing language models, these approaches typically rely on a pre-existing classifier for undesired outputs. This limits their application to situations where the type of harmful behavior is known with precision beforehand. However, this skips a central challenge of red teaming: developing a contextual understanding of the behaviors that a model can exhibit. Furthermore, when such a classifier already exists, red teaming has limited marginal value because the classifier could simply be used to filter training data or model outputs. In this work, we consider red teaming under the assumption that the adversary is working from a high-level, abstract specification of undesired behavior. The red team is expected to refine/extend this specification and identify methods to elicit this behavior from the model. Our red teaming framework consists of three steps: 1) Exploring the model's behavior in the desired context; 2) Establishing a measurement of undesired behavior (e.g., a classifier trained to reflect human evaluations); and 3) Exploiting the model's flaws using this measure and an established red teaming methodology. We apply this approach to red team GPT-2 and GPT-3 models to systematically discover classes of prompts that elicit toxic and dishonest statements. In doing so, we also construct and release the CommonClaim dataset of 20,000 statements that have been labeled by human subjects as common-knowledge-true, common-knowledge-false, or neither. Code is available at https://github.com/thestephencasper/explore_establish_exploit_llms. CommonClaim is available at https://github.com/Algorithmic-Alignment-Lab/CommonClaim.