Leveraging Reasoning with Guidelines to Elicit and Utilize Knowledge for Enhancing Safety Alignment

Training safe LLMs is one of the most critical research challenge. However, the commonly used method, Refusal Training (RT), struggles to generalize against various OOD jailbreaking attacks. Many safety training methods have been proposed to address this issue. While they offer valuable insights, we aim to complement this line of research by investigating whether OOD attacks truly exceed the capability of RT model. Conducting evaluation with BoN, we observe significant improvements on generalization as N increases. This underscores that the model possesses sufficient safety-related latent knowledge, but RT fails to consistently elicit this knowledge when addressing OOD attacks. Further analysis based on domain adaptation reveals that training with direct refusal causes model to rely on superficial shortcuts, resulting in learning of non-robust representation mappings. Based on our findings, we propose training model to perform safety reasoning for each query. Reasoning supervision encourages model to perform more computations, explicitly eliciting and using latent knowledge through reasoning. To achieve this, we synthesize reasoning supervision based on pre-guidelines, training the model to reason in alignment with them, thereby effectively eliciting and utilizing latent knowledge from diverse perspectives. Extensive experiments show that our method significantly improves generalization performance against OOD attacks.

Improving Your Model Ranking on Chatbot Arena by Vote Rigging

Chatbot Arena is a popular platform for evaluating LLMs by pairwise battles, where users vote for their preferred response from two randomly sampled anonymous models. While Chatbot Arena is widely regarded as a reliable LLM ranking leaderboard, we show that crowdsourced voting can be rigged to improve (or decrease) the ranking of a target model $m_{t}$. We first introduce a straightforward target-only rigging strategy that focuses on new battles involving $m_{t}$, identifying it via watermarking or a binary classifier, and exclusively voting for $m_{t}$ wins. However, this strategy is practically inefficient because there are over $190$ models on Chatbot Arena and on average only about $1\%$ of new battles will involve $m_{t}$. To overcome this, we propose omnipresent rigging strategies, exploiting the Elo rating mechanism of Chatbot Arena that any new vote on a battle can influence the ranking of the target model $m_{t}$, even if $m_{t}$ is not directly involved in the battle. We conduct experiments on around $1.7$ million historical votes from the Chatbot Arena Notebook, showing that omnipresent rigging strategies can improve model rankings by rigging only hundreds of new votes. While we have evaluated several defense mechanisms, our findings highlight the importance of continued efforts to prevent vote rigging. Our code is available at https://github.com/sail-sg/Rigging-ChatbotArena.

Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense

Backdoor attacks pose a significant threat to Deep Neural Networks (DNNs) as they allow attackers to manipulate model predictions with backdoor triggers. To address these security vulnerabilities, various backdoor purification methods have been proposed to purify compromised models. Typically, these purified models exhibit low Attack Success Rates (ASR), rendering them resistant to backdoored inputs. However, Does achieving a low ASR through current safety purification methods truly eliminate learned backdoor features from the pretraining phase? In this paper, we provide an affirmative answer to this question by thoroughly investigating the Post-Purification Robustness of current backdoor purification methods. We find that current safety purification methods are vulnerable to the rapid re-learning of backdoor behavior, even when further fine-tuning of purified models is performed using a very small number of poisoned samples. Based on this, we further propose the practical Query-based Reactivation Attack (QRA) which could effectively reactivate the backdoor by merely querying purified models. We find the failure to achieve satisfactory post-tuning robustness stems from the insufficient deviation of purified models from the backdoored model along the backdoor-connected path. To improve the post-purification robustness, we propose a straightforward tuning defense, Path-Aware Minimization (PAM), which promotes deviation along backdoor-connected paths with extra model updates. Extensive experiments demonstrate that PAM significantly improves post-purification robustness while maintaining a good clean accuracy and low ASR. Our work provides a new perspective on understanding the effectiveness of backdoor safety tuning and highlights the importance of faithfully assessing the model's safety.

Defense Against Syntactic Textual Backdoor Attacks with Token Substitution

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same triggers as a certain class. Prior backdoor defense methods primarily target special token-based triggers, leaving syntax-based triggers insufficiently addressed. To fill this gap, this paper proposes a novel online defense algorithm that effectively counters syntax-based as well as special token-based backdoor attacks. The algorithm replaces semantically meaningful words in sentences with entirely different ones but preserves the syntactic templates or special tokens, and then compares the predicted labels before and after the substitution to determine whether a sentence contains triggers. Experimental results confirm the algorithm's performance against these two types of triggers, offering a comprehensive defense strategy for model integrity.

One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts

Large Language Models (LLMs) exhibit strong generalization capabilities to novel tasks when prompted with language instructions and in-context demos. Since this ability sensitively depends on the quality of prompts, various methods have been explored to automate the instruction design. While these methods demonstrated promising results, they also restricted the searched prompt to one instruction. Such simplification significantly limits their capacity, as a single demo-free instruction might not be able to cover the entire complex problem space of the targeted task. To alleviate this issue, we adopt the Mixture-of-Expert paradigm and divide the problem space into a set of sub-regions; Each sub-region is governed by a specialized expert, equipped with both an instruction and a set of demos. A two-phase process is developed to construct the specialized expert for each region: (1) demo assignment: Inspired by the theoretical connection between in-context learning and kernel regression, we group demos into experts based on their semantic similarity; (2) instruction assignment: A region-based joint search of an instruction per expert complements the demos assigned to it, yielding a synergistic effect. The resulting method, codenamed Mixture-of-Prompts (MoP), achieves an average win rate of 81% against prior arts across several major benchmarks.

MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?

Humans are prone to cognitive distortions -- biased thinking patterns that lead to exaggerated responses to specific stimuli, albeit in very different contexts. This paper demonstrates that advanced Multimodal Large Language Models (MLLMs) exhibit similar tendencies. While these models are designed to respond queries under safety mechanism, they sometimes reject harmless queries in the presence of certain visual stimuli, disregarding the benign nature of their contexts. As the initial step in investigating this behavior, we identify three types of stimuli that trigger the oversensitivity of existing MLLMs: Exaggerated Risk, Negated Harm, and Counterintuitive Interpretation. To systematically evaluate MLLMs' oversensitivity to these stimuli, we propose the Multimodal OverSenSitivity Benchmark (MOSSBench). This toolkit consists of 300 manually collected benign multimodal queries, cross-verified by third-party reviewers (AMT). Empirical studies using MOSSBench on 20 MLLMs reveal several insights: (1). Oversensitivity is prevalent among SOTA MLLMs, with refusal rates reaching up to 76% for harmless queries. (2). Safer models are more oversensitive: increasing safety may inadvertently raise caution and conservatism in the model's responses. (3). Different types of stimuli tend to cause errors at specific stages -- perception, intent reasoning, and safety judgement -- in the response process of MLLMs. These findings highlight the need for refined safety mechanisms that balance caution with contextually appropriate responses, improving the reliability of MLLMs in real-world applications. We make our project available at https://turningpoint-ai.github.io/MOSSBench/.

Understanding the Impact of Negative Prompts: When and How Do They Take Effect?

The concept of negative prompts, emerging from conditional generation models like Stable Diffusion, allows users to specify what to exclude from the generated images.%, demonstrating significant practical efficacy. Despite the widespread use of negative prompts, their intrinsic mechanisms remain largely unexplored. This paper presents the first comprehensive study to uncover how and when negative prompts take effect. Our extensive empirical analysis identifies two primary behaviors of negative prompts. Delayed Effect: The impact of negative prompts is observed after positive prompts render corresponding content. Deletion Through Neutralization: Negative prompts delete concepts from the generated image through a mutual cancellation effect in latent space with positive prompts. These insights reveal significant potential real-world applications; for example, we demonstrate that negative prompts can facilitate object inpainting with minimal alterations to the background via a simple adaptive algorithm. We believe our findings will offer valuable insights for the community in capitalizing on the potential of negative prompts.

The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise

Diffusion models have achieved remarkable success in text-to-image generation tasks; however, the role of initial noise has been rarely explored. In this study, we identify specific regions within the initial noise image, termed trigger patches, that play a key role for object generation in the resulting images. Notably, these patches are ``universal'' and can be generalized across various positions, seeds, and prompts. To be specific, extracting these patches from one noise and injecting them into another noise leads to object generation in targeted areas. We identify these patches by analyzing the dispersion of object bounding boxes across generated images, leading to the development of a posterior analysis technique. Furthermore, we create a dataset consisting of Gaussian noises labeled with bounding boxes corresponding to the objects appearing in the generated images and train a detector that identifies these patches from the initial noise. To explain the formation of these patches, we reveal that they are outliers in Gaussian noise, and follow distinct distributions through two-sample tests. Finally, we find the misalignment between prompts and the trigger patch patterns can result in unsuccessful image generations. The study proposes a reject-sampling strategy to obtain optimal noise, aiming to improve prompt adherence and positional diversity in image generation.

Invisible Backdoor Attacks on Diffusion Models

In recent years, diffusion models have achieved remarkable success in the realm of high-quality image generation, garnering increased attention. This surge in interest is paralleled by a growing concern over the security threats associated with diffusion models, largely attributed to their susceptibility to malicious exploitation. Notably, recent research has brought to light the vulnerability of diffusion models to backdoor attacks, enabling the generation of specific target images through corresponding triggers. However, prevailing backdoor attack methods rely on manually crafted trigger generation functions, often manifesting as discernible patterns incorporated into input noise, thus rendering them susceptible to human detection. In this paper, we present an innovative and versatile optimization framework designed to acquire invisible triggers, enhancing the stealthiness and resilience of inserted backdoors. Our proposed framework is applicable to both unconditional and conditional diffusion models, and notably, we are the pioneers in demonstrating the backdooring of diffusion models within the context of text-guided image editing and inpainting pipelines. Moreover, we also show that the backdoors in the conditional generation can be directly applied to model watermarking for model ownership verification, which further boosts the significance of the proposed framework. Extensive experiments on various commonly used samplers and datasets verify the efficacy and stealthiness of the proposed framework. Our code is publicly available at https://github.com/invisibleTriggerDiffusion/invisible_triggers_for_diffusion.

Input Snapshots Fusion for Scalable Discrete Dynamic Graph Nerual Networks

Dynamic graphs are ubiquitous in the real world, yet there is a lack of suitable theoretical frameworks to effectively extend existing static graph models into the temporal domain. Additionally, for link prediction tasks on discrete dynamic graphs, the requirement of substantial GPU memory to store embeddings of all nodes hinders the scalability of existing models. In this paper, we introduce an Input {\bf S}napshots {\bf F}usion based {\bf Dy}namic {\bf G}raph Neural Network (SFDyG). By eliminating the partitioning of snapshots within the input window, we obtain a multi-graph (more than one edge between two nodes). Subsequently, by introducing a graph denoising problem with the assumption of temporal decayed smoothing, we integrate Hawkes process theory into Graph Neural Networks to model the generated multi-graph. Furthermore, based on the multi-graph, we propose a scalable three-step mini-batch training method and demonstrate its equivalence to full-batch training counterpart. Our experiments, conducted on eight distinct dynamic graph datasets for future link prediction tasks, revealed that SFDyG generally surpasses related methods.