ICLR 2025 Papers

Text-to-image diffusion models have achieved unprecedented proficiency in generating realistic images. However, their inherent tendency to memorize and replicate training data during inference raises significant concerns, including potential copyright infringement. In response, various methods have been proposed to evaluate, detect, and mitigate memorization. Our analysis reveals that existing approaches significantly underperform in handling local memorization, where only specific image regions are memorized, compared to global memorization, where the entire image is replicated. Also, they cannot locate the local memorization regions, making it hard to investigate locally. To address these, we identify a novel "bright ending" (BE) anomaly in diffusion models prone to memorizing training images. BE refers to a distinct cross-attention pattern observed in text-to-image diffusion models, where memorized image patches exhibit significantly greater attention to the final text token during the last inference step than non-memorized patches. This pattern highlights regions where the generated image replicates training data and enables efficient localization of memorized regions. Equipped with this, we propose a simple yet effective method to integrate BE into existing frameworks, significantly improving their performance by narrowing the performance gap caused by local memorization. Our results not only validate the successful execution of the new localization task but also establish new state-of-the-art performance across all existing tasks, underscoring the significance of the BE phenomenon.

Model inversion attacks (MIAs) aim to reconstruct the private training data by accessing the public model, raising concerns about privacy leakage. Black-box MIAs, where attackers can only query the model and obtain outputs, are closer to real-world scenarios. The latest black-box attacks have outperformed state-of-the-art white-box attacks, and existing defenses cannot resist them effectively. To fill this gap, we propose Stealthy Shield Defense (SSD), a post-processing algorithm against black-box MIAs. Our idea is to modify the model's outputs to minimize the conditional mutual information (CMI). We mathematically prove that CMI is a special case of Information Bottleneck (IB), and thus inherits the benefits of IB---making predictions less dependent on inputs and more dependent on ground truths. This theoretically guarantees our effectiveness, both in resisting MIAs and preserving utility. To minimize CMI, we formulate a convex optimization problem and solve it via the water-filling method. Without the need to retrain the model, our defense is plug-and-play and easy to deploy. Experimental results indicate that SSD outperforms existing defenses, in terms of MIA resistance and model's utility, across various attack algorithms, private datasets, and model architectures. Our code is available at https://github.com/ZhuangQu/Stealthy-Shield-Defense.

We introduce DarkBench, a comprehensive benchmark for detecting dark design patterns—manipulative techniques that influence user behavior—in interactions with large language models (LLMs). Our benchmark comprises 660 prompts across six categories: brand bias, user retention, sycophancy, anthropomorphism, harmful generation, and sneaking. We evaluate models from five leading companies (OpenAI, Anthropic, Meta, Mistral, Google) and find that some LLMs are explicitly designed to favor their developers' products and exhibit untruthful communication, among other manipulative behaviors. Companies developing LLMs should recognize and mitigate the impact of dark design patterns to promote more ethical Al.

Variational Autoencoders (VAEs) have become increasingly popular and deployed in safety-critical applications. In such applications, we want to give certified probabilistic guarantees on performance under adversarial attacks. We propose a novel method, CIVET, for certified training of VAEs. CIVET depends on the key insight that we can bound worst-case VAE error by bounding the error on carefully chosen support sets at the latent layer. We show this point mathematically and present a novel training algorithm utilizing this insight. We show in an extensive evaluation across different datasets (in both the wireless and vision application areas), architectures, and perturbation magnitudes that our method outperforms SOTA methods achieving good standard performance with strong robustness guarantees.

Data attribution aims to quantify the contribution of individual training data points to the outputs of an AI model, which has been used to measure the value of training data and compensate data providers. Given the impact on financial decisions and compensation mechanisms, a critical question arises concerning the adversarial robustness of data attribution methods. However, there has been little to no systematic research addressing this issue. In this work, we aim to bridge this gap by detailing a threat model with clear assumptions about the adversary's goal and capabilities and proposing principled adversarial attack methods on data attribution. We present two methods, *Shadow Attack* and *Outlier Attack*, which generate manipulated datasets to inflate the compensation adversarially. The Shadow Attack leverages knowledge about the data distribution in the AI applications, and derives adversarial perturbations through "shadow training", a technique commonly used in membership inference attacks. In contrast, the Outlier Attack does not assume any knowledge about the data distribution and relies solely on black-box queries to the target model's predictions. It exploits an inductive bias present in many data attribution methods - outlier data points are more likely to be influential - and employs adversarial examples to generate manipulated datasets. Empirically, in image classification and text generation tasks, the Shadow Attack can inflate the data-attribution-based compensation by at least 200%, while the Outlier Attack achieves compensation inflation ranging from 185% to as much as 643%. Our implementation is ready at https://github.com/TRAIS-Lab/adversarial-attack-data-attribution

Auto-regressive large language models (LLMs) have yielded impressive performance in many real-world tasks. However, the new paradigm of these LLMs also exposes novel threats. In this paper, we explore their vulnerability to inference cost attacks, where a malicious user crafts Engorgio prompts to intentionally increase the computation cost and latency of the inference process. We design Engorgio, a novel methodology, to efficiently generate adversarial Engorgio prompts to affect the target LLM's service availability. Engorgio has the following two technical contributions. (1) We employ a parameterized distribution to track LLMs' prediction trajectory. (2) Targeting the auto-regressive nature of LLMs' inference process, we propose novel loss functions to stably suppress the appearance of the <EOS> token, whose occurrence will interrupt the LLM's generation process. We conduct extensive experiments on 13 open-sourced LLMs with parameters ranging from 125M to 30B. The results show that Engorgio prompts can successfully induce LLMs to generate abnormally long outputs (i.e., roughly 2-13$\times$ longer to reach 90\%+ of the output length limit) in a white-box scenario and our real-world experiment demonstrates Engergio's threat to LLM service with limited computing resources. The code is released at https://github.com/jianshuod/Engorgio-prompt.

We study the Differential Privacy (DP) guarantee of hidden-state Noisy-SGD algorithms over a bounded domain. Standard privacy analysis for Noisy-SGD assumes all internal states are revealed, which leads to a divergent R\'enyi DP bound with respect to the number of iterations. Ye & Shokri (2022) and Altschuler & Talwar (2022) proved convergent bounds for smooth (strongly) convex losses, and raise open questions about whether these assumptions can be relaxed. We provide positive answers by proving convergent R\'enyi DP bound for non-convex non-smooth losses, where we show that requiring losses to have H\"older continuous gradient is sufficient. We also provide a strictly better privacy bound compared to state-of-the-art results for smooth strongly convex losses. Our analysis relies on the improvement of shifted divergence analysis in multiple aspects, including forward Wasserstein distance tracking, identifying the optimal shifts allocation, and the H\"older reduction lemma. Our results further elucidate the benefit of hidden-state analysis for DP and its applicability.

Existing preference optimization objectives for language model alignment require additional hyperparameters that must be extensively tuned to achieve optimal performance, increasing both the complexity and time required for fine-tuning large language models. In this paper, we propose a simple yet effective hyperparameter-free preference optimization algorithm for alignment. We observe that promising performance can be achieved simply by optimizing inverse perplexity, which is calculated as the inverse of the exponentiated average log-likelihood of the chosen and rejected responses in the preference dataset. The resulting simple learning objective, SimPER, is easy to implement and eliminates the need for expensive hyperparameter tuning and a reference model, making it both computationally and memory efficient. Extensive experiments on widely used real-world benchmarks, including MT-Bench, AlpacaEval 2, and 10 key benchmarks of the Open LLM Leaderboard with 5 base models, demonstrate that SimPER consistently and significantly outperforms existing approaches—even without any hyperparameters or a reference model. For example, despite its simplicity, SimPER outperforms state-of-the-art methods by up to 5.7 points on AlpacaEval 2 and achieves the highest average ranking across 10 benchmarks on the Open LLM Leaderboard. The source code for SimPER is publicly available at: https://github.com/tengxiao1/SimPER.

With the rise of large language models (LLMs), increasing research has recognized their risk of leaking personally identifiable information (PII) under malicious attacks. Although efforts have been made to protect PII in LLMs, existing methods struggle to balance privacy protection with maintaining model utility. In this paper, inspired by studies of amnesia in cognitive science, we propose a novel approach, Proactive Privacy Amnesia (PPA), to safeguard PII in LLMs while preserving their utility. This mechanism works by actively identifying and forgetting key memories most closely associated with PII in sequences, followed by a memory implanting using suitable substitute memories to maintain the LLM’s functionality. We conduct evaluations across multiple models to protect common PII, such as phone numbers and physical addresses, against prevalent PII-targeted attacks, demonstrating the superiority of our method compared with other existing defensive techniques. The results show that our PPA method completely eliminates the risk of phone number exposure by 100% and significantly reduces the risk of physical address exposure by 9.8% – 87.6%, all while maintaining comparable model utility performance.

Explaining Graph Neural Network (XGNN) has gained growing attention to facilitate the trust of using GNNs, which is the mainstream method to learn graph data. Despite their growing attention, Existing XGNNs focus on improving the explanation performance, and its robustness under attacks is largely unexplored. We noticed that an adversary can slightly perturb the graph structure such that the explanation result of XGNNs is largely changed. Such vulnerability of XGNNs could cause serious issues particularly in safety/security-critical applications. In this paper, we take the first step to study the robustness of XGNN against graph perturbation attacks, and propose XGNNCert, the first provably robust XGNN. Particularly, our XGNNCert can provably ensure the explanation result for a graph under the worst-case graph perturbation attack is close to that without the attack, while not affecting the GNN prediction, when the number of perturbed edges is bounded. Evaluation results on multiple graph datasets and GNN explainers show the effectiveness of XGNNCert.

Existing score-based adversarial attacks mainly focus on crafting $top$-1 adversarial examples against classifiers with single-label classification. Their attack success rate and query efficiency are often less than satisfactory, particularly under small perturbation requirements; moreover, the vulnerability of classifiers with multi-label learning is yet to be studied. In this paper, we propose a comprehensive surrogate free score-based attack, named \b geometric \b score-based \b black-box \b attack (GSBA$^K$), to craft adversarial examples in an aggressive $top$-$K$ setting for both untargeted and targeted attacks, where the goal is to change the $top$-$K$ predictions of the target classifier. We introduce novel gradient-based methods to find a good initial boundary point to attack. Our iterative method employs novel gradient estimation techniques, particularly effective in $top$-$K$ setting, on the decision boundary to effectively exploit the geometry of the decision boundary. Additionally, GSBA$^K$ can be used to attack against classifiers with $top$-$K$ multi-label learning. Extensive experiential results on ImageNet and PASCAL VOC datasets validate the effectiveness of GSBA$^K$ in crafting $top$-$K$ adversarial examples.

Anti-backdoor learning, aiming to train clean models directly from poisoned datasets, serves as an important defense method for backdoor attack. However, existing methods usually fail to recover backdoored samples to their original, correct labels and suffer from poor generalization to large pre-trained models due to its non end-to end training, making them unsuitable for protecting the increasingly prevalent large pre-trained models. To bridge the gap, we first revisit the anti-backdoor learning problem from a causal perspective. Our theoretical causal analysis reveals that incorporating \emph{\textbf{both}} images and the associated attack indicators preserves the model's integrity. Building on the theoretical analysis, we introduce an end-to-end method, Mind Control through Causal Inference (MCCI), to train clean models directly from poisoned datasets. This approach leverages both the image and the attack indicator to train the model. Based on this training paradigm, the model’s perception of whether an input is clean or backdoored can be controlled. Typically, by introducing fake non-attack indicators, the model perceives all inputs as clean and makes correct predictions, even for poisoned samples. Extensive experiments demonstrate that our method achieves state-of-the-art performance, efficiently recovering the original correct predictions for poisoned samples and enhancing accuracy on clean samples.

We show that even the most recent safety-aligned LLMs are not robust to simple *adaptive* jailbreaking attacks. First, we demonstrate how to successfully leverage access to *logprobs* for jailbreaking: we initially design an adversarial prompt template (sometimes adapted to the target LLM), and then we apply random search on a suffix to maximize a target logprob (e.g., of the token *``Sure''*), potentially with multiple restarts. In this way, we achieve 100\% attack success rate---according to GPT-4 as a judge---on Vicuna-13B, Mistral-7B, Phi-3-Mini, Nemotron-4-340B, Llama-2-Chat-7B/13B/70B, Llama-3-Instruct-8B, Gemma-7B, GPT-3.5, GPT-4o, and R2D2 from HarmBench that was adversarially trained against the GCG attack. We also show how to jailbreak *all* Claude models---that do not expose logprobs---via either a transfer or prefilling attack with a *100\% success rate*. In addition, we show how to use random search on a restricted set of tokens for finding trojan strings in poisoned models---a task that shares many similarities with jailbreaking---which is the algorithm that brought us the *first place* in a recent trojan detection competition. The common theme behind these attacks is that *adaptivity* is crucial: different models are vulnerable to different prompting templates (e.g., R2D2 is very sensitive to in-context learning prompts), some models have unique vulnerabilities based on their APIs (e.g., prefilling for Claude), and in some settings, it is crucial to restrict the token search space based on prior knowledge (e.g., for trojan detection). For reproducibility purposes, we provide the code, logs, and jailbreak artifacts in the JailbreakBench format at https://github.com/tml-epfl/llm-adaptive-attacks.

We consider differentially private counting when each data point consists of $d$ bits satisfying a partial order. Our main technical contribution is a problem-specific $K$-norm mechanism that runs in time $O(d^2)$. Experiments show that, depending on the partial order in question, our solution dominates existing pure differentially private mechanisms and can reduce their error by an order of magnitude or more.

Document Visual Question Answering (DocVQA) has introduced a new paradigm for end-to-end document understanding, and quickly became one of the standard benchmarks for multimodal LLMs. Automating document processing workflows, driven by DocVQA models, presents significant potential for many business sectors. However, documents tend to contain highly sensitive information, raising concerns about privacy risks associated with training such DocVQA models. One significant privacy vulnerability, exploited by the membership inference attack, is the possibility for an adversary to determine if a particular record was part of the model's training data. In this paper, we introduce two novel membership inference attacks tailored specifically to DocVQA models. These attacks are designed for two different adversarial scenarios: a white-box setting, where the attacker has full access to the model architecture and parameters, and a black-box setting, where only the model's outputs are available. Notably, our attacks assume the adversary lacks access to auxiliary datasets, which is more realistic in practice but also more challenging. Our unsupervised methods outperform existing state-of-the-art membership inference attacks across a variety of DocVQA models and datasets, demonstrating their effectiveness and highlighting the privacy risks in this domain.

Recently Diffusion-based Purification (DiffPure) has been recognized as an effective defense method against adversarial examples. However, we find DiffPure which directly employs the original pre-trained diffusion models for adversarial purification, to be suboptimal. This is due to an inherent trade-off between noise purification performance and data recovery quality. Additionally, the reliability of existing evaluations for DiffPure is questionable, as they rely on weak adaptive attacks. In this work, we propose a novel Adversarial Diffusion Bridge Model, termed ADBM. ADBM directly constructs a reverse bridge from the diffused adversarial data back to its original clean examples, enhancing the purification capabilities of the original diffusion models. Through theoretical analysis and experimental validation across various scenarios, ADBM has proven to be a superior and robust defense mechanism, offering significant promise for practical applications. Code is available at https://github.com/LixiaoTHU/ADBM.

In this paper, we introduce the $\ell_p^p$-error metric (for $p \geq 2$) when answering linear queries under the constraint of differential privacy. We characterize such an error under $(\epsilon,\delta)$-differential privacy in the natural add/remove model. Before this paper, tight characterization in the hardness of privately answering linear queries was known under $\ell_2^2$-error metric (Edmonds et al. 2020) and $\ell_p^2$-error metric for unbiased mechanisms in the substitution model (Nikolov et al. 2024). As a direct consequence of our results, we give tight bounds on answering prefix sum and parity queries under differential privacy for all constant $p$ in terms of the $\ell_p^p$ error, generalizing the bounds in Hhenzinger et al. for $p=2$.

Many stakeholders---from model developers to policymakers---seek to minimize the risks of large language models (LLMs). Key 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 openly available. 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 parameters. However, we caution against over-reliance on such methods in their current state. Through several case studies, we demonstrate that even the evaluation of 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 failure modes that we identify and suggest that future research carefully cabin claims to more constrained, well-defined, and rigorously examined threat models, which can provide useful and candid assessments to stakeholders.

Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a simple set of benign relearning attacks. With access to only a small and potentially loosely related set of data, we find that we can “jog” the memory of unlearned models to reverse the effects of unlearning. For example, we show that relearning on public medical articles can lead an unlearned LLM to output harmful knowledge about bioweapons, and relearning general wiki information about the book series Harry Potter can force the model to output verbatim memorized text. We formalize this unlearning-relearning pipeline, explore the attack across three popular unlearning benchmarks, and discuss future directions and guidelines that result from our study. Our work indicates that current approximate unlearning methods simply suppress the model outputs and fail to robustly forget target knowledge in the LLMs.