Identifying and Mitigating the Security Risks of Generative AI

Every major technical invention resurfaces the dual-use dilemma -- the new technology has the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such as large language models (LLMs) and diffusion models, have shown remarkable capabilities (e.g., in-context learning, code-completion, and text-to-image generation and editing). However, GenAI can be used just as well by attackers to generate new attacks and increase the velocity and efficacy of existing attacks. This paper reports the findings of a workshop held at Google (co-organized by Stanford University and the University of Wisconsin-Madison) on the dual-use dilemma posed by GenAI. This paper is not meant to be comprehensive, but is rather an attempt to synthesize some of the interesting findings from the workshop. We discuss short-term and long-term goals for the community on this topic. We hope this paper provides both a launching point for a discussion on this important topic as well as interesting problems that the research community can work to address.

Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks

Adversarial examples threaten the integrity of machine learning systems with alarming success rates even under constrained black-box conditions. Stateful defenses have emerged as an effective countermeasure, detecting potential attacks by maintaining a buffer of recent queries and detecting new queries that are too similar. However, these defenses fundamentally pose a trade-off between attack detection and false positive rates, and this trade-off is typically optimized by hand-picking feature extractors and similarity thresholds that empirically work well. There is little current understanding as to the formal limits of this trade-off and the exact properties of the feature extractors/underlying problem domain that influence it. This work aims to address this gap by offering a theoretical characterization of the trade-off between detection and false positive rates for stateful defenses. We provide upper bounds for detection rates of a general class of feature extractors and analyze the impact of this trade-off on the convergence of black-box attacks. We then support our theoretical findings with empirical evaluations across multiple datasets and stateful defenses.

Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems

With the emergence of large foundational models, model-serving systems are becoming popular. In such a system, users send the queries to the server and specify the desired performance metrics (e.g., accuracy, latency, etc.). The server maintains a set of models (model zoo) in the back-end and serves the queries based on the specified metrics. This paper examines the security, specifically robustness against model extraction attacks, of such systems. Existing black-box attacks cannot be directly applied to extract a victim model, as models hide among the model zoo behind the inference serving interface, and attackers cannot identify which model is being used. An intermediate step is required to ensure that every input query gets the output from the victim model. To this end, we propose a query-efficient fingerprinting algorithm to enable the attacker to trigger any desired model consistently. We show that by using our fingerprinting algorithm, model extraction can have fidelity and accuracy scores within $1\%$ of the scores obtained if attacking in a single-model setting and up to $14.6\%$ gain in accuracy and up to $7.7\%$ gain in fidelity compared to the naive attack. Finally, we counter the proposed attack with a noise-based defense mechanism that thwarts fingerprinting by adding noise to the specified performance metrics. Our defense strategy reduces the attack's accuracy and fidelity by up to $9.8\%$ and $4.8\%$, respectively (on medium-sized model extraction). We show that the proposed defense induces a fundamental trade-off between the level of protection and system goodput, achieving configurable and significant victim model extraction protection while maintaining acceptable goodput ($>80\%$). We provide anonymous access to our code.

Two Heads are Better than One: Towards Better Adversarial Robustness by Combining Transduction and Rejection

Both transduction and rejection have emerged as important techniques for defending against adversarial perturbations. A recent work by Tram\`er showed that, in the rejection-only case (no transduction), a strong rejection-solution can be turned into a strong (but computationally inefficient) non-rejection solution. This detector-to-classifier reduction has been mostly applied to give evidence that certain claims of strong selective-model solutions are susceptible, leaving the benefits of rejection unclear. On the other hand, a recent work by Goldwasser et al. showed that rejection combined with transduction can give provable guarantees (for certain problems) that cannot be achieved otherwise. Nevertheless, under recent strong adversarial attacks (GMSA, which has been shown to be much more effective than AutoAttack against transduction), Goldwasser et al.'s work was shown to have low performance in a practical deep-learning setting. In this paper, we take a step towards realizing the promise of transduction+rejection in more realistic scenarios. Theoretically, we show that a novel application of Tram\`er's classifier-to-detector technique in the transductive setting can give significantly improved sample-complexity for robust generalization. While our theoretical construction is computationally inefficient, it guides us to identify an efficient transductive algorithm to learn a selective model. Extensive experiments using state of the art attacks (AutoAttack, GMSA) show that our solutions provide significantly better robust accuracy.

Rethink Diversity in Deep Learning Testing

Deep neural networks (DNNs) have demonstrated extraordinary capabilities and are an integral part of modern software systems. However, they also suffer from various vulnerabilities such as adversarial attacks and unfairness. Testing deep learning (DL) systems is therefore an important task, to detect and mitigate those vulnerabilities. Motivated by the success of traditional software testing, which often employs diversity heuristics, various diversity measures on DNNs have been proposed to help efficiently expose the buggy behavior of DNNs. In this work, we argue that many DNN testing tasks should be treated as directed testing problems rather than general-purpose testing tasks, because these tasks are specific and well-defined. Hence, the diversity-based approach is less effective. Following our argument based on the semantics of DNNs and the testing goal, we derive $6$ metrics that can be used for DNN testing and carefully analyze their application scopes. We empirically show their efficacy in exposing bugs in DNNs compared to recent diversity-based metrics. Moreover, we also notice discrepancies between the practices of the software engineering (SE) community and the DL community. We point out some of these gaps, and hopefully, this can lead to bridging the SE practice and DL findings.

Stratified Adversarial Robustness with Rejection

Recently, there is an emerging interest in adversarially training a classifier with a rejection option (also known as a selective classifier) for boosting adversarial robustness. While rejection can incur a cost in many applications, existing studies typically associate zero cost with rejecting perturbed inputs, which can result in the rejection of numerous slightly-perturbed inputs that could be correctly classified. In this work, we study adversarially-robust classification with rejection in the stratified rejection setting, where the rejection cost is modeled by rejection loss functions monotonically non-increasing in the perturbation magnitude. We theoretically analyze the stratified rejection setting and propose a novel defense method -- Adversarial Training with Consistent Prediction-based Rejection (CPR) -- for building a robust selective classifier. Experiments on image datasets demonstrate that the proposed method significantly outperforms existing methods under strong adaptive attacks. For instance, on CIFAR-10, CPR reduces the total robust loss (for different rejection losses) by at least 7.3% under both seen and unseen attacks.

ASPEST: Bridging the Gap Between Active Learning and Selective Prediction

Selective prediction aims to learn a reliable model that abstains from making predictions when the model uncertainty is high. These predictions can then be deferred to a human expert for further evaluation. In many real-world scenarios, however, the distribution of test data is different from the training data. This results in more inaccurate predictions, necessitating increased human labeling, which is difficult and expensive in many scenarios. Active learning circumvents this difficulty by only querying the most informative examples and, in several cases, has been shown to lower the overall labeling effort. In this work, we bridge the gap between selective prediction and active learning, proposing a new learning paradigm called active selective prediction which learns to query more informative samples from the shifted target domain while increasing accuracy and coverage. For this new problem, we propose a simple but effective solution, ASPEST, that trains ensembles of model snapshots using self-training with their aggregated outputs as pseudo labels. Extensive experiments on several image, text and structured datasets with domain shifts demonstrate that active selective prediction can significantly outperform prior work on selective prediction and active learning (e.g. on the MNIST$\to$SVHN benchmark with the labeling budget of 100, ASPEST improves the AUC metric from 79.36% to 88.84%) and achieves more optimal utilization of humans in the loop.

Efficient Symbolic Reasoning for Neural-Network Verification

The neural network has become an integral part of modern software systems. However, they still suffer from various problems, in particular, vulnerability to adversarial attacks. In this work, we present a novel program reasoning framework for neural-network verification, which we refer to as symbolic reasoning. The key components of our framework are the use of the symbolic domain and the quadratic relation. The symbolic domain has very flexible semantics, and the quadratic relation is quite expressive. They allow us to encode many verification problems for neural networks as quadratic programs. Our scheme then relaxes the quadratic programs to semidefinite programs, which can be efficiently solved. This framework allows us to verify various neural-network properties under different scenarios, especially those that appear challenging for non-symbolic domains. Moreover, it introduces new representations and perspectives for the verification tasks. We believe that our framework can bring new theoretical insights and practical tools to verification problems for neural networks.

Investigating Stateful Defenses Against Black-Box Adversarial Examples

Defending machine-learning (ML) models against white-box adversarial attacks has proven to be extremely difficult. Instead, recent work has proposed stateful defenses in an attempt to defend against a more restricted black-box attacker. These defenses operate by tracking a history of incoming model queries, and rejecting those that are suspiciously similar. The current state-of-the-art stateful defense Blacklight was proposed at USENIX Security '22 and claims to prevent nearly 100% of attacks on both the CIFAR10 and ImageNet datasets. In this paper, we observe that an attacker can significantly reduce the accuracy of a Blacklight-protected classifier (e.g., from 82.2% to 6.4% on CIFAR10) by simply adjusting the parameters of an existing black-box attack. Motivated by this surprising observation, since existing attacks were evaluated by the Blacklight authors, we provide a systematization of stateful defenses to understand why existing stateful defense models fail. Finally, we propose a stronger evaluation strategy for stateful defenses comprised of adaptive score and hard-label based black-box attacks. We use these attacks to successfully reduce even reconfigured versions of Blacklight to as low as 0% robust accuracy.