Weiran Lin

Weiran Lin, Keane Lucas, Neo Eyal et al. · cmu

Machine-learning models are known to be vulnerable to evasion attacks that perturb model inputs to induce misclassifications. In this work, we identify real-world scenarios where the true threat cannot be assessed accurately by existing attacks. Specifically, we find that conventional metrics measuring targeted and untargeted robustness do not appropriately reflect a model's ability to withstand attacks from one set of source classes to another set of target classes. To address the shortcomings of existing methods, we formally define a new metric, termed group-based robustness, that complements existing metrics and is better-suited for evaluating model performance in certain attack scenarios. We show empirically that group-based robustness allows us to distinguish between models' vulnerability against specific threat models in situations where traditional robustness metrics do not apply. Moreover, to measure group-based robustness efficiently and accurately, we 1) propose two loss functions and 2) identify three new attack strategies. We show empirically that with comparable success rates, finding evasive samples using our new loss functions saves computation by a factor as large as the number of targeted classes, and finding evasive samples using our new attack strategies saves time by up to 99\% compared to brute-force search methods. Finally, we propose a defense method that increases group-based robustness by up to 3.52$\times$.

Mingzhang Yin, Ruijiang Gao, Weiran Lin et al.

Designing products to meet consumers' preferences is essential for a business's success. We propose the Gradient-based Survey (GBS), a discrete choice experiment for multiattribute product design. The experiment elicits consumer preferences through a sequence of paired comparisons for partial profiles. GBS adaptively constructs paired comparison questions based on the respondents' previous choices. Unlike the traditional random utility maximization paradigm, GBS is robust to model misspecification by not requiring a parametric utility model. Cross-pollinating the machine learning and experiment design, GBS is scalable to products with hundreds of attributes and can design personalized products for heterogeneous consumers. We demonstrate the advantage of GBS in accuracy and sample efficiency compared to the existing parametric and nonparametric methods in simulations.

Nathaniel Li, Alexander Pan, Anjali Gopal et al. · berkeley, cmu

The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs. However, current evaluations are private, preventing further research into mitigating risk. Furthermore, they focus on only a few, highly specific pathways for malicious use. To fill these gaps, we publicly release the Weapons of Mass Destruction Proxy (WMDP) benchmark, a dataset of 3,668 multiple-choice questions that serve as a proxy measurement of hazardous knowledge in biosecurity, cybersecurity, and chemical security. WMDP was developed by a consortium of academics and technical consultants, and was stringently filtered to eliminate sensitive information prior to public release. WMDP serves two roles: first, as an evaluation for hazardous knowledge in LLMs, and second, as a benchmark for unlearning methods to remove such hazardous knowledge. To guide progress on unlearning, we develop RMU, a state-of-the-art unlearning method based on controlling model representations. RMU reduces model performance on WMDP while maintaining general capabilities in areas such as biology and computer science, suggesting that unlearning may be a concrete path towards reducing malicious use from LLMs. We release our benchmark and code publicly at https://wmdp.ai

Henry Wong, Clement Fung, Weiran Lin et al.

To autonomously control vehicles, driving agents use outputs from a combination of machine-learning (ML) models, controller logic, and custom modules. Although numerous prior works have shown that adversarial examples can mislead ML models used in autonomous driving contexts, it remains unclear if these attacks are effective at producing harmful driving actions for various agents, environments, and scenarios. To assess the risk of adversarial examples to autonomous driving, we evaluate attacks against a variety of driving agents, rather than against ML models in isolation. To support this evaluation, we leverage CARLA, an urban driving simulator, to create and evaluate adversarial examples. We create adversarial patches designed to stop or steer driving agents, stream them into the CARLA simulator at runtime, and evaluate them against agents from the CARLA Leaderboard, a public repository of best-performing autonomous driving agents from an annual research competition. Unlike prior work, we evaluate attacks against autonomous driving systems without creating or modifying any driving-agent code and against all parts of the agent included with the ML model. We perform a case-study investigation of two attack strategies against three open-source driving agents from the CARLA Leaderboard across multiple driving scenarios, lighting conditions, and locations. Interestingly, we show that, although some attacks can successfully mislead ML models into predicting erroneous stopping or steering commands, some driving agents use modules, such as PID control or GPS-based rules, that can overrule attacker-manipulated predictions from ML models.

Weiran Lin, Anna Gerchanovsky, Omer Akgul et al.

Writing effective prompts for large language models (LLM) can be unintuitive and burdensome. In response, services that optimize or suggest prompts have emerged. While such services can reduce user effort, they also introduce a risk: the prompt provider can subtly manipulate prompts to produce heavily biased LLM responses. In this work, we show that subtle synonym replacements in prompts can increase the likelihood (by a difference up to 78%) that LLMs mention a target concept (e.g., a brand, political party, nation). We substantiate our observations through a user study, showing that our adversarially perturbed prompts 1) are indistinguishable from unaltered prompts by humans, 2) push LLMs to recommend target concepts more often, and 3) make users more likely to notice target concepts, all without arousing suspicion. The practicality of this attack has the potential to undermine user autonomy. Among other measures, we recommend implementing warnings against using prompts from untrusted parties.

Weiran Lin, Keane Lucas, Lujo Bauer et al.

We propose new, more efficient targeted white-box attacks against deep neural networks. Our attacks better align with the attacker's goal: (1) tricking a model to assign higher probability to the target class than to any other class, while (2) staying within an $ε$-distance of the attacked input. First, we demonstrate a loss function that explicitly encodes (1) and show that Auto-PGD finds more attacks with it. Second, we propose a new attack method, Constrained Gradient Descent (CGD), using a refinement of our loss function that captures both (1) and (2). CGD seeks to satisfy both attacker objectives -- misclassification and bounded $\ell_{p}$-norm -- in a principled manner, as part of the optimization, instead of via ad hoc post-processing techniques (e.g., projection or clipping). We show that CGD is more successful on CIFAR10 (0.9--4.2%) and ImageNet (8.6--13.6%) than state-of-the-art attacks while consuming less time (11.4--18.8%). Statistical tests confirm that our attack outperforms others against leading defenses on different datasets and values of $ε$.