OverThink: Slowdown Attacks on Reasoning LLMs

We increase overhead for applications that rely on reasoning LLMs-we force models to spend an amplified number of reasoning tokens, i.e., "overthink", to respond to the user query while providing contextually correct answers. The adversary performs an OVERTHINK attack by injecting decoy reasoning problems into the public content that is used by the reasoning LLM (e.g., for RAG applications) during inference time. Due to the nature of our decoy problems (e.g., a Markov Decision Process), modified texts do not violate safety guardrails. We evaluated our attack across closed-(OpenAI o1, o1-mini, o3-mini) and open-(DeepSeek R1) weights reasoning models on the FreshQA and SQuAD datasets. Our results show up to 18x slowdown on FreshQA dataset and 46x slowdown on SQuAD dataset. The attack also shows high transferability across models. To protect applications, we discuss and implement defenses leveraging LLM-based and system design approaches. Finally, we discuss societal, financial, and energy impacts of OVERTHINK attack which could amplify the costs for third-party applications operating reasoning models.

OVERTHINKING: Slowdown Attacks on Reasoning LLMs

We increase overhead for applications that rely on reasoning LLMs-we force models to spend an amplified number of reasoning tokens, i.e., "overthink", to respond to the user query while providing contextually correct answers. The adversary performs an OVERTHINK attack by injecting decoy reasoning problems into the public content that is used by the reasoning LLM (e.g., for RAG applications) during inference time. Due to the nature of our decoy problems (e.g., a Markov Decision Process), modified texts do not violate safety guardrails. We evaluated our attack across closed-(OpenAI o1, o1-mini, o3-mini) and open-(DeepSeek R1) weights reasoning models on the FreshQA and SQuAD datasets. Our results show up to 46x slowdown and high transferability of the attack across models. To protect applications, we discuss and implement defenses leveraging LLM-based and system design approaches. Finally, we discuss societal, financial, and energy impacts of OVERTHINK attack which could amplify the costs for third party applications operating reasoning models.

ULTra: Unveiling Latent Token Interpretability in Transformer Based Understanding

Transformers have revolutionized Computer Vision (CV) and Natural Language Processing (NLP) through self-attention mechanisms. However, due to their complexity, their latent token representations are often difficult to interpret. We introduce a novel framework that interprets Transformer embeddings, uncovering meaningful semantic patterns within them. Based on this framework, we demonstrate that zero-shot unsupervised semantic segmentation can be performed effectively without any fine-tuning using a model pre-trained for tasks other than segmentation. Our method reveals the inherent capacity of Transformer models for understanding input semantics and achieves state-of-the-art performance in semantic segmentation, outperforming traditional segmentation models. Specifically, our approach achieves an accuracy of 67.2 % and an mIoU of 32.9 % on the COCO-Stuff dataset, as well as an mIoU of 51.9 % on the PASCAL VOC dataset. Additionally, we validate our interpretability framework on LLMs for text summarization, demonstrating its broad applicability and robustness.

Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors

Despite significant advancements, large language models (LLMs) still struggle with providing accurate answers when lacking domain-specific or up-to-date knowledge. Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external knowledge bases, but it also introduces new attack surfaces. In this paper, we investigate data extraction attacks targeting the knowledge databases of RAG systems. We demonstrate that previous attacks on RAG largely depend on the instruction-following capabilities of LLMs, and that simple fine-tuning can reduce the success rate of such attacks to nearly zero. This makes these attacks impractical since fine-tuning is a common practice when deploying LLMs in specific domains. To further reveal the vulnerability, we propose to backdoor RAG, where a small portion of poisoned data is injected during the fine-tuning phase to create a backdoor within the LLM. When this compromised LLM is integrated into a RAG system, attackers can exploit specific triggers in prompts to manipulate the LLM to leak documents from the retrieval database. By carefully designing the poisoned data, we achieve both verbatim and paraphrased document extraction. We show that with only 3\% poisoned data, our method achieves an average success rate of 79.7\% in verbatim extraction on Llama2-7B, with a ROUGE-L score of 64.21, and a 68.6\% average success rate in paraphrased extraction, with an average ROUGE score of 52.6 across four datasets. These results underscore the privacy risks associated with the supply chain when deploying RAG systems.

Bias Similarity Across Large Language Models

Bias in machine learning models has been a chronic problem, especially as these models influence decision-making in human society. In generative AI, such as Large Language Models, the impact of bias is even more profound compared to the classification models. LLMs produce realistic and human-like content that users may unconsciously trust, which could perpetuate harmful stereotypes to the uncontrolled public. It becomes particularly concerning when utilized in journalism or education. While prior studies have explored and quantified bias in individual AI models, no work has yet compared bias similarity across different LLMs. To fill this gap, we take a comprehensive look at ten open- and closed-source LLMs from four model families, assessing the extent of biases through output distribution. Using two datasets-one containing 4k questions and another with one million questions for each of the four bias dimensions -- we measure functional similarity to understand how biases manifest across models. Our findings reveal that 1) fine-tuning does not significantly alter output distributions, which would limit its ability to mitigate bias, 2) LLMs within the same family tree do not produce similar output distributions, implying that addressing bias in one model could have limited implications for others in the same family, and 3) there is a possible risk of training data information leakage, raising concerns about privacy and data security. Our analysis provides insight into LLM behavior and highlights potential risks in real-world deployment.

Injecting Bias in Text-To-Image Models via Composite-Trigger Backdoors

Recent advances in large text-conditional image generative models such as Stable Diffusion, Midjourney, and DALL-E 3 have revolutionized the field of image generation, allowing users to produce high-quality, realistic images from textual prompts. While these developments have enhanced artistic creation and visual communication, they also present an underexplored attack opportunity: the possibility of inducing biases by an adversary into the generated images for malicious intentions, e.g., to influence society and spread propaganda. In this paper, we demonstrate the possibility of such a bias injection threat by an adversary who backdoors such models with a small number of malicious data samples; the implemented backdoor is activated when special triggers exist in the input prompt of the backdoored models. On the other hand, the model's utility is preserved in the absence of the triggers, making the attack highly undetectable. We present a novel framework that enables efficient generation of poisoning samples with composite (multi-word) triggers for such an attack. Our extensive experiments using over 1 million generated images and against hundreds of fine-tuned models demonstrate the feasibility of the presented backdoor attack. We illustrate how these biases can bypass conventional detection mechanisms, highlighting the challenges in proving the existence of biases within operational constraints. Our cost analysis confirms the low financial barrier to executing such attacks, underscoring the need for robust defensive strategies against such vulnerabilities in text-to-image generation models.

PostMark: A Robust Blackbox Watermark for Large Language Models

The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits, which LLM API providers are loath to share due to fears of model distillation. As such, these watermarks must be implemented independently by each LLM provider. In this paper, we develop PostMark, a modular post-hoc watermarking procedure in which an input-dependent set of words (determined via a semantic embedding) is inserted into the text after the decoding process has completed. Critically, PostMark does not require logit access, which means it can be implemented by a third party. We also show that PostMark is more robust to paraphrasing attacks than existing watermarking methods: our experiments cover eight baseline algorithms, five base LLMs, and three datasets. Finally, we evaluate the impact of PostMark on text quality using both automated and human assessments, highlighting the trade-off between quality and robustness to paraphrasing. We release our code, outputs, and annotations at https://github.com/lilakk/PostMark.

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification

We present a simple yet effective method to improve the robustness of Convolutional Neural Networks (CNNs) against adversarial examples by post-processing an adversarially trained model. Our technique, MeanSparse, cascades the activation functions of a trained model with novel operators that sparsify mean-centered feature vectors. This is equivalent to reducing feature variations around the mean, and we show that such reduced variations merely affect the model's utility, yet they strongly attenuate the adversarial perturbations and decrease the attacker's success rate. Our experiments show that, when applied to the top models in the RobustBench leaderboard, it achieves a new robustness record of 72.08% (from 71.07%) and 59.64% (from 59.56%) on CIFAR-10 and ImageNet, respectively, in term of AutoAttack accuracy. Code is available at https://github.com/SPIN-UMass/MeanSparse

OSLO: One-Shot Label-Only Membership Inference Attacks

We introduce One-Shot Label-Only (OSLO) membership inference attacks (MIAs), which accurately infer a given sample's membership in a target model's training set with high precision using just \emph{a single query}, where the target model only returns the predicted hard label. This is in contrast to state-of-the-art label-only attacks which require $\sim6000$ queries, yet get attack precisions lower than OSLO's. OSLO leverages transfer-based black-box adversarial attacks. The core idea is that a member sample exhibits more resistance to adversarial perturbations than a non-member. We compare OSLO against state-of-the-art label-only attacks and demonstrate that, despite requiring only one query, our method significantly outperforms previous attacks in terms of precision and true positive rate (TPR) under the same false positive rates (FPR). For example, compared to previous label-only MIAs, OSLO achieves a TPR that is 7$\times$ to 28$\times$ stronger under a 0.1\% FPR on CIFAR10 for a ResNet model. We evaluated multiple defense mechanisms against OSLO.

Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images

With the digital imagery landscape rapidly evolving, image stocks and AI-generated image marketplaces have become central to visual media. Traditional stock images now exist alongside innovative platforms that trade in prompts for AI-generated visuals, driven by sophisticated APIs like DALL-E 3 and Midjourney. This paper studies the possibility of employing multi-modal models with enhanced visual understanding to mimic the outputs of these platforms, introducing an original attack strategy. Our method leverages fine-tuned CLIP models, a multi-label classifier, and the descriptive capabilities of GPT-4V to create prompts that generate images similar to those available in marketplaces and from premium stock image providers, yet at a markedly lower expense. In presenting this strategy, we aim to spotlight a new class of economic and security considerations within the realm of digital imagery. Our findings, supported by both automated metrics and human assessment, reveal that comparable visual content can be produced for a fraction of the prevailing market prices ($0.23 - $0.27 per image), emphasizing the need for awareness and strategic discussions about the integrity of digital media in an increasingly AI-integrated landscape. Our work also contributes to the field by assembling a dataset consisting of approximately 19 million prompt-image pairs generated by the popular Midjourney platform, which we plan to release publicly.