arXiv subjects

Milad Nasr

Publications and source records attributed to Milad Nasr.

At least 37 records · Page 2Linked to original sources

arXiv2025

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses

We introduce AutoAdvExBench, a benchmark to evaluate if large language models (LLMs) can autonomously exploit defenses to adversarial examples. Unlike existing security benchmarks that often serve as proxies for real-world tasks, bench directly measures LLMs' success on tasks regularly performed by machine learning security experts. This approach offers a significant advantage: if a LLM could solve the challenges presented in bench, it would immediately present practical utility for adversarial machine learning researchers. We then design a strong agent that is capable of breaking 75% of CTF-like ("homework exercise") adversarial example defenses. However, we show that this agent is only able to succeed on 13% of the real-world defenses in our benchmark, indicating the large gap between difficulty in attacking "real" code, and CTF-like code. In contrast, a stronger LLM that can attack 21% of real defenses only succeeds on 54% of CTF-like defenses. We make this benchmark available at https://github.com/ethz-spylab/AutoAdvExBench.

cs.CR↗

arXiv2025

Private Fine-tuning of Large Language Models with Zeroth-order Optimization

Differentially private stochastic gradient descent (DP-SGD) allows models to be trained in a privacy-preserving manner, but has proven difficult to scale to the era of foundation models. We introduce DP-ZO, a private fine-tuning framework for large language models by privatizing zeroth order optimization methods. A key insight into the design of our method is that the direction of the gradient in the zeroth-order optimization we use is random and the only information from training data is the step size, i.e., a scalar. Therefore, we only need to privatize the scalar step size, which is memory-efficient. DP-ZO provides a strong privacy-utility trade-off across different tasks, and model sizes that are comparable to DP-SGD in $(\varepsilon,δ)$-DP. Notably, DP-ZO possesses significant advantages over DP-SGD in memory efficiency, and obtains higher utility in $\varepsilon$-DP when using the Laplace mechanism.

cs.LG↗

arXiv2025

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards

It is now common to evaluate Large Language Models (LLMs) by having humans manually vote to evaluate model outputs, in contrast to typical benchmarks that evaluate knowledge or skill at some particular task. Chatbot Arena, the most popular benchmark of this type, ranks models by asking users to select the better response between two randomly selected models (without revealing which model was responsible for the generations). These platforms are widely trusted as a fair and accurate measure of LLM capabilities. In this paper, we show that if bot protection and other defenses are not implemented, these voting-based benchmarks are potentially vulnerable to adversarial manipulation. Specifically, we show that an attacker can alter the leaderboard (to promote their favorite model or demote competitors) at the cost of roughly a thousand votes (verified in a simulated, offline version of Chatbot Arena). Our attack consists of two steps: first, we show how an attacker can determine which model was used to generate a given reply with more than $95\%$ accuracy; and then, the attacker can use this information to consistently vote for (or against) a target model. Working with the Chatbot Arena developers, we identify, propose, and implement mitigations to improve the robustness of Chatbot Arena against adversarial manipulation, which, based on our analysis, substantially increases the cost of such attacks. Some of these defenses were present before our collaboration, such as bot protection with Cloudflare, malicious user detection, and rate limiting. Others, including reCAPTCHA and login are being integrated to strengthen the security in Chatbot Arena.

cs.LG↗

arXiv2024

On Evaluating the Durability of Safeguards for Open-Weight LLMs

Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are customizable via fine-tuning or when model weights are fully open. In response, several recent studies have proposed methods to produce durable LLM safeguards for open-weight LLMs that can withstand adversarial modifications of the model's weights via fine-tuning. This holds the promise of raising adversaries' costs even under strong threat models where adversaries can directly fine-tune model weights. However, in this paper, we urge for more careful characterization of the limits of these approaches. Through several case studies, we demonstrate that even evaluating these defenses is exceedingly difficult and can easily mislead audiences into thinking that safeguards are more durable than they really are. We draw lessons from the evaluation pitfalls that we identify and suggest future research carefully cabin claims to more constrained, well-defined, and rigorously examined threat models, which can provide more useful and candid assessments to stakeholders.

cs.CR↗

arXiv2024

Query-Based Adversarial Prompt Generation

Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks work either in the white-box setting (with full access to the model weights), or through transferability: the phenomenon that adversarial examples crafted on one model often remain effective on other models. We improve on prior work with a query-based attack that leverages API access to a remote language model to construct adversarial examples that cause the model to emit harmful strings with (much) higher probability than with transfer-only attacks. We validate our attack on GPT-3.5 and OpenAI's safety classifier; we can cause GPT-3.5 to emit harmful strings that current transfer attacks fail at, and we can evade the safety classifier with nearly 100% probability.

cs.CL↗

arXiv2024

Remote Timing Attacks on Efficient Language Model Inference

Scaling up language models has significantly increased their capabilities. But larger models are slower models, and so there is now an extensive body of work (e.g., speculative sampling or parallel decoding) that improves the (average case) efficiency of language model generation. But these techniques introduce data-dependent timing characteristics. We show it is possible to exploit these timing differences to mount a timing attack. By monitoring the (encrypted) network traffic between a victim user and a remote language model, we can learn information about the content of messages by noting when responses are faster or slower. With complete black-box access, on open source systems we show how it is possible to learn the topic of a user's conversation (e.g., medical advice vs. coding assistance) with 90%+ precision, and on production systems like OpenAI's ChatGPT and Anthropic's Claude we can distinguish between specific messages or infer the user's language. We further show that an active adversary can leverage a boosting attack to recover PII placed in messages (e.g., phone numbers or credit card numbers) for open source systems. We conclude with potential defenses and directions for future work.

cs.CR↗

arXiv2024

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy

Machine unlearning algorithms, designed for selective removal of training data from models, have emerged as a promising approach to growing privacy concerns. In this work, we expose a critical yet underexplored vulnerability in the deployment of unlearning systems: the assumption that the data requested for removal is always part of the original training set. We present a threat model where an attacker can degrade model accuracy by submitting adversarial unlearning requests for data not present in the training set. We propose white-box and black-box attack algorithms and evaluate them through a case study on image classification tasks using the CIFAR-10 and ImageNet datasets, targeting a family of widely used unlearning methods. Our results show extremely poor test accuracy following the attack: 3.6% on CIFAR-10 and 0.4% on ImageNet for white-box attacks, and 8.5% on CIFAR-10 and 1.3% on ImageNet for black-box attacks. Additionally, we evaluate various verification mechanisms to detect the legitimacy of unlearning requests and reveal the challenges in verification, as most of the mechanisms fail to detect stealthy attacks without severely impairing their ability to process valid requests. These findings underscore the urgent need for research on more robust request verification methods and unlearning protocols, should the deployment of machine unlearning systems become more prevalent in the future.

cs.CR↗

arXiv2024

Avoiding Generative Model Writer's Block With Embedding Nudging

Generative image models, since introduction, have become a global phenomenon. From new arts becoming possible to new vectors of abuse, many new capabilities have become available. One of the challenging issues with generative models is controlling the generation process specially to prevent specific generations classes or instances . There are several reasons why one may want to control the output of generative models, ranging from privacy and safety concerns to application limitations or user preferences To address memorization and privacy challenges, there has been considerable research dedicated to filtering prompts or filtering the outputs of these models. What all these solutions have in common is that at the end of the day they stop the model from producing anything, hence limiting the usability of the model. In this paper, we propose a method for addressing this usability issue by making it possible to steer away from unwanted concepts (when detected in model's output) and still generating outputs. In particular we focus on the latent diffusion image generative models and how one can prevent them to generate particular images while generating similar images with limited overhead. We focus on mitigating issues like image memorization, demonstrating our technique's effectiveness through qualitative and quantitative evaluations. Our method successfully prevents the generation of memorized training images while maintaining comparable image quality and relevance to the unmodified model.

cs.LG↗

arXiv2024

Privacy Side Channels in Machine Learning Systems

Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include components for training data filtering, output monitoring, and more. In this work, we introduce privacy side channels: attacks that exploit these system-level components to extract private information at far higher rates than is otherwise possible for standalone models. We propose four categories of side channels that span the entire ML lifecycle (training data filtering, input preprocessing, output post-processing, and query filtering) and allow for enhanced membership inference, data extraction, and even novel threats such as extraction of users' test queries. For example, we show that deduplicating training data before applying differentially-private training creates a side-channel that completely invalidates any provable privacy guarantees. We further show that systems which block language models from regenerating training data can be exploited to exfiltrate private keys contained in the training set--even if the model did not memorize these keys. Taken together, our results demonstrate the need for a holistic, end-to-end privacy analysis of machine learning systems.

cs.CR↗

arXiv2024

Stealing Part of a Production Language Model

We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like OpenAI's ChatGPT or Google's PaLM-2. Specifically, our attack recovers the embedding projection layer (up to symmetries) of a transformer model, given typical API access. For under \$20 USD, our attack extracts the entire projection matrix of OpenAI's Ada and Babbage language models. We thereby confirm, for the first time, that these black-box models have a hidden dimension of 1024 and 2048, respectively. We also recover the exact hidden dimension size of the gpt-3.5-turbo model, and estimate it would cost under $2,000 in queries to recover the entire projection matrix. We conclude with potential defenses and mitigations, and discuss the implications of possible future work that could extend our attack.

cs.CR↗

arXiv2024

Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models

We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable, making them difficult to directly DP-train with since common techniques require per-example gradients. To address this issue, we propose an approach that prioritizes ensuring query privacy prior to training a deep retrieval system. Our method employs DP language models (LMs) to generate private synthetic queries representative of the original data. These synthetic queries can be used in downstream retrieval system training without compromising privacy. Our approach demonstrates a significant enhancement in retrieval quality compared to direct DP-training, all while maintaining query-level privacy guarantees. This work highlights the potential of harnessing LMs to overcome limitations in standard DP-training methods.

cs.CL↗

arXiv2024

Are aligned neural networks adversarially aligned?

Large language models are now tuned to align with the goals of their creators, namely to be "helpful and harmless." These models should respond helpfully to user questions, but refuse to answer requests that could cause harm. However, adversarial users can construct inputs which circumvent attempts at alignment. In this work, we study adversarial alignment, and ask to what extent these models remain aligned when interacting with an adversarial user who constructs worst-case inputs (adversarial examples). These inputs are designed to cause the model to emit harmful content that would otherwise be prohibited. We show that existing NLP-based optimization attacks are insufficiently powerful to reliably attack aligned text models: even when current NLP-based attacks fail, we can find adversarial inputs with brute force. As a result, the failure of current attacks should not be seen as proof that aligned text models remain aligned under adversarial inputs. However the recent trend in large-scale ML models is multimodal models that allow users to provide images that influence the text that is generated. We show these models can be easily attacked, i.e., induced to perform arbitrary un-aligned behavior through adversarial perturbation of the input image. We conjecture that improved NLP attacks may demonstrate this same level of adversarial control over text-only models.

cs.CL↗

arXiv2024

Auditing Private Prediction

Differential privacy (DP) offers a theoretical upper bound on the potential privacy leakage of analgorithm, while empirical auditing establishes a practical lower bound. Auditing techniques exist forDP training algorithms. However machine learning can also be made private at inference. We propose thefirst framework for auditing private prediction where we instantiate adversaries with varying poisoningand query capabilities. This enables us to study the privacy leakage of four private prediction algorithms:PATE [Papernot et al., 2016], CaPC [Choquette-Choo et al., 2020], PromptPATE [Duan et al., 2023],and Private-kNN [Zhu et al., 2020]. To conduct our audit, we introduce novel techniques to empiricallyevaluate privacy leakage in terms of Renyi DP. Our experiments show that (i) the privacy analysis ofprivate prediction can be improved, (ii) algorithms which are easier to poison lead to much higher privacyleakage, and (iii) the privacy leakage is significantly lower for adversaries without query control than thosewith full control.

cs.CR↗

arXiv2023

Universal and Transferable Adversarial Attacks on Aligned Language Models

Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some success at circumventing these measures -- so-called "jailbreaks" against LLMs -- these attacks have required significant human ingenuity and are brittle in practice. In this paper, we propose a simple and effective attack method that causes aligned language models to generate objectionable behaviors. Specifically, our approach finds a suffix that, when attached to a wide range of queries for an LLM to produce objectionable content, aims to maximize the probability that the model produces an affirmative response (rather than refusing to answer). However, instead of relying on manual engineering, our approach automatically produces these adversarial suffixes by a combination of greedy and gradient-based search techniques, and also improves over past automatic prompt generation methods. Surprisingly, we find that the adversarial prompts generated by our approach are quite transferable, including to black-box, publicly released LLMs. Specifically, we train an adversarial attack suffix on multiple prompts (i.e., queries asking for many different types of objectionable content), as well as multiple models (in our case, Vicuna-7B and 13B). When doing so, the resulting attack suffix is able to induce objectionable content in the public interfaces to ChatGPT, Bard, and Claude, as well as open source LLMs such as LLaMA-2-Chat, Pythia, Falcon, and others. In total, this work significantly advances the state-of-the-art in adversarial attacks against aligned language models, raising important questions about how such systems can be prevented from producing objectionable information. Code is available at github.com/llm-attacks/llm-attacks.

cs.CL↗

arXiv2023

Report of the 1st Workshop on Generative AI and Law

This report presents the takeaways of the inaugural Workshop on Generative AI and Law (GenLaw), held in July 2023. A cross-disciplinary group of practitioners and scholars from computer science and law convened to discuss the technical, doctrinal, and policy challenges presented by law for Generative AI, and by Generative AI for law, with an emphasis on U.S. law in particular. We begin the report with a high-level statement about why Generative AI is both immensely significant and immensely challenging for law. To meet these challenges, we conclude that there is an essential need for 1) a shared knowledge base that provides a common conceptual language for experts across disciplines; 2) clarification of the distinctive technical capabilities of generative-AI systems, as compared and contrasted to other computer and AI systems; 3) a logical taxonomy of the legal issues these systems raise; and, 4) a concrete research agenda to promote collaboration and knowledge-sharing on emerging issues at the intersection of Generative AI and law. In this report, we synthesize the key takeaways from the GenLaw workshop that begin to address these needs. All of the listed authors contributed to the workshop upon which this report is based, but they and their organizations do not necessarily endorse all of the specific claims in this report.

cs.CY↗

arXiv2023

Scalable Extraction of Training Data from (Production) Language Models

This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training dataset. We show an adversary can extract gigabytes of training data from open-source language models like Pythia or GPT-Neo, semi-open models like LLaMA or Falcon, and closed models like ChatGPT. Existing techniques from the literature suffice to attack unaligned models; in order to attack the aligned ChatGPT, we develop a new divergence attack that causes the model to diverge from its chatbot-style generations and emit training data at a rate 150x higher than when behaving properly. Our methods show practical attacks can recover far more data than previously thought, and reveal that current alignment techniques do not eliminate memorization.

cs.LG↗

arXiv2023

Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy

Studying data memorization in neural language models helps us understand the risks (e.g., to privacy or copyright) associated with models regurgitating training data and aids in the development of countermeasures. Many prior works -- and some recently deployed defenses -- focus on "verbatim memorization", defined as a model generation that exactly matches a substring from the training set. We argue that verbatim memorization definitions are too restrictive and fail to capture more subtle forms of memorization. Specifically, we design and implement an efficient defense that perfectly prevents all verbatim memorization. And yet, we demonstrate that this "perfect" filter does not prevent the leakage of training data. Indeed, it is easily circumvented by plausible and minimally modified "style-transfer" prompts -- and in some cases even the non-modified original prompts -- to extract memorized information. We conclude by discussing potential alternative definitions and why defining memorization is a difficult yet crucial open question for neural language models.

cs.LG↗

arXiv2023

Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System

Neural language models are increasingly deployed into APIs and websites that allow a user to pass in a prompt and receive generated text. Many of these systems do not reveal generation parameters. In this paper, we present methods to reverse-engineer the decoding method used to generate text (i.e., top-$k$ or nucleus sampling). Our ability to discover which decoding strategy was used has implications for detecting generated text. Additionally, the process of discovering the decoding strategy can reveal biases caused by selecting decoding settings which severely truncate a model's predicted distributions. We perform our attack on several families of open-source language models, as well as on production systems (e.g., ChatGPT).

cs.LG↗