AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment

With the growing adoption of reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs), the risk of backdoor installation during alignment has increased, leading to unintended and harmful behaviors. Existing backdoor triggers are typically limited to fixed word patterns, making them detectable during data cleaning and easily removable post-poisoning. In this work, we explore the use of prompt-specific paraphrases as backdoor triggers, enhancing their stealth and resistance to removal during LLM alignment. We propose AdvBDGen, an adversarially fortified generative fine-tuning framework that automatically generates prompt-specific backdoors that are effective, stealthy, and transferable across models. AdvBDGen employs a generator-discriminator pair, fortified by an adversary, to ensure the installability and stealthiness of backdoors. It enables the crafting and successful installation of complex triggers using as little as 3% of the fine-tuning data. Once installed, these backdoors can jailbreak LLMs during inference, demonstrate improved stability against perturbations compared to traditional constant triggers, and are more challenging to remove. These findings underscore an urgent need for the research community to develop more robust defenses against adversarial backdoor threats in LLM alignment.

Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash against the very values alignment seeks to protect. In this paper, we propose the first method to auto-generate diverse, content-controlled, and model-dependent pseudo-harmful prompts. Using this method, we construct an evaluation dataset called PHTest, which is ten times larger than existing datasets, covers more false refusal patterns, and separately labels controversial prompts. We evaluate 20 LLMs on PHTest, uncovering new insights due to its scale and labeling. Our findings reveal a trade-off between minimizing false refusals and improving safety against jailbreak attacks. Moreover, we show that many jailbreak defenses significantly increase the false refusal rates, thereby undermining usability. Our method and dataset can help developers evaluate and fine-tune safer and more usable LLMs. Our code and dataset are available at https://github.com/umd-huang-lab/FalseRefusal

Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?

Large Language Models (LLMs) have demonstrated impressive capabilities in generating diverse and contextually rich text. However, concerns regarding copyright infringement arise as LLMs may inadvertently produce copyrighted material. In this paper, we first investigate the effectiveness of watermarking LLMs as a deterrent against the generation of copyrighted texts. Through theoretical analysis and empirical evaluation, we demonstrate that incorporating watermarks into LLMs significantly reduces the likelihood of generating copyrighted content, thereby addressing a critical concern in the deployment of LLMs. Additionally, we explore the impact of watermarking on Membership Inference Attacks (MIAs), which aim to discern whether a sample was part of the pretraining dataset and may be used to detect copyright violations. Surprisingly, we find that watermarking adversely affects the success rate of MIAs, complicating the task of detecting copyrighted text in the pretraining dataset. Finally, we propose an adaptive technique to improve the success rate of a recent MIA under watermarking. Our findings underscore the importance of developing adaptive methods to study critical problems in LLMs with potential legal implications.

More Context, Less Distraction: Visual Classification by Inferring and Conditioning on Contextual Attributes

CLIP, as a foundational vision language model, is widely used in zero-shot image classification due to its ability to understand various visual concepts and natural language descriptions. However, how to fully leverage CLIP's unprecedented human-like understanding capabilities to achieve better zero-shot classification is still an open question. This paper draws inspiration from the human visual perception process: a modern neuroscience view suggests that in classifying an object, humans first infer its class-independent attributes (e.g., background and orientation) which help separate the foreground object from the background, and then make decisions based on this information. Inspired by this, we observe that providing CLIP with contextual attributes improves zero-shot classification and mitigates reliance on spurious features. We also observe that CLIP itself can reasonably infer the attributes from an image. With these observations, we propose a training-free, two-step zero-shot classification method named PerceptionCLIP. Given an image, it first infers contextual attributes (e.g., background) and then performs object classification conditioning on them. Our experiments show that PerceptionCLIP achieves better generalization, group robustness, and better interpretability. For example, PerceptionCLIP with ViT-L/14 improves the worst group accuracy by 16.5% on the Waterbirds dataset and by 3.5% on CelebA.

Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes

Quantization is a popular technique that $transforms$ the parameter representation of a neural network from floating-point numbers into lower-precision ones ($e.g.$, 8-bit integers). It reduces the memory footprint and the computational cost at inference, facilitating the deployment of resource-hungry models. However, the parameter perturbations caused by this transformation result in $behavioral$ $disparities$ between the model before and after quantization. For example, a quantized model can misclassify some test-time samples that are otherwise classified correctly. It is not known whether such differences lead to a new security vulnerability. We hypothesize that an adversary may control this disparity to introduce specific behaviors that activate upon quantization. To study this hypothesis, we weaponize quantization-aware training and propose a new training framework to implement adversarial quantization outcomes. Following this framework, we present three attacks we carry out with quantization: (i) an indiscriminate attack for significant accuracy loss; (ii) a targeted attack against specific samples; and (iii) a backdoor attack for controlling the model with an input trigger. We further show that a single compromised model defeats multiple quantization schemes, including robust quantization techniques. Moreover, in a federated learning scenario, we demonstrate that a set of malicious participants who conspire can inject our quantization-activated backdoor. Lastly, we discuss potential counter-measures and show that only re-training consistently removes the attack artifacts. Our code is available at https://github.com/Secure-AI-Systems-Group/Qu-ANTI-zation