相关论文: From Insight to Exploit: Leveraging LLM Collaborat…

We introduce a novel framework that transforms the resource-intensive (adversarial) prompt optimization problem into an \emph{efficient, amortized inference task}. Our core insight is that pretrained, non-autoregressive generative LLMs,…

The growing deployment of deep learning models in real-world environments has intensified the need for efficient inference under strict latency and resource constraints. To meet these demands, dynamic deep learning systems (DDLSs) have…

The increasing deployment of Large Language Models (LLMs) in various applications necessitates a rigorous evaluation of their robustness against adversarial attacks. In this paper, we present a comprehensive study on the robustness of GPT…

With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has recently made great progress. However, there are few studies to examine the security of LLMs in math solving ability. Instead of attacking…

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples. Adversarial examples are malicious images with visually imperceptible perturbations. While these carefully crafted perturbations restricted with tight…

Large Language Models (LLMs) are being enhanced with the ability to use tools and to process multiple modalities. These new capabilities bring new benefits and also new security risks. In this work, we show that an attacker can use visual…

The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object…

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…

As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely…

Despite the wide use of machine learning in adversarial settings including computer security, recent studies have demonstrated vulnerabilities to evasion attacks---carefully crafted adversarial samples that closely resemble legitimate…

Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

Large Language Models (LLMs) excel at code generation, yet their outputs often contain subtle bugs, for which effective test cases are a critical bottleneck. Existing test generation methods, whether based on prompting or supervised…

Inspired by the success of large language models (LLMs), there is a significant research shift from traditional graph learning methods to LLM-based graph frameworks, formally known as GraphLLMs. GraphLLMs leverage the reasoning power of…

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…

Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm…

As large language models (LLMs) grow more powerful, ensuring their safety against misuse becomes crucial. While researchers have focused on developing robust defenses, no method has yet achieved complete invulnerability to attacks. We…

Adversarial examples are maliciously modified inputs created to fool deep neural networks (DNN). The discovery of such inputs presents a major issue to the expansion of DNN-based solutions. Many researchers have already contributed to the…

Recent efforts within the AI community have yielded impressive results towards "soft theorem proving" over natural language sentences using language models. We propose a novel, generative adversarial framework for probing and improving…

Cybersecurity threats continue to increase, with a growing number of previously unknown attacks each year targeting both large corporations and smaller entities. This scenario demands the implementation of advanced security measures, not…