相关论文: Exploiting the Index Gradients for Optimization-Ba…

Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a closer look at the optimization objective of adversarial…

Large Language Models (LLMs) are often asked to generate structured outputs that obey precise syntactic rules, such as code snippets or formatted data. Grammar-constrained decoding (GCD) can guarantee that LLM outputs matches such rules by…

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…

Large language models (LLMs) have revolutionized lots of fields of research. Although it is well-known that fine-tuning is essential for enhancing the capabilities of LLMs, existing research suggests that there is potential redundancy in…

Large language models (LLMs) remain susceptible to jailbreak and direct prompt-injection attacks, yet the strongest defensive filters frequently over-refuse benign queries and degrade user experience. Previous work on jailbreak and prompt…

Defending large language models (LLMs) against jailbreak attacks, such as Greedy Coordinate Gradient (GCG), remains a challenge, particularly under adaptive threat models where an attacker directly targets the defense mechanism. JBShield, a…

Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies often rely on brute-force optimization or manual design, failing…

Retrieval Augmented Generation (RAG) frameworks improve the accuracy of large language models (LLMs) by integrating external knowledge from retrieved documents, thereby overcoming the limitations of models' static intrinsic knowledge.…

The robustness of large language models (LLMs) becomes increasingly important as their use rapidly grows in a wide range of domains. Retrieval-Augmented Generation (RAG) is considered as a means to improve the trustworthiness of text…

We present BadGD, a unified theoretical framework that exposes the vulnerabilities of gradient descent algorithms through strategic backdoor attacks. Backdoor attacks involve embedding malicious triggers into a training dataset to disrupt…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed…

Retrieval-Augmented Generation (RAG) systems extend large language models (LLMs) with external knowledge sources but introduce new attack surfaces through the retrieval pipeline. In particular, adversaries can poison retrieval corpora so…

The widespread deployment of large language models (LLMs) has raised growing concerns about their misuse risks and associated safety issues. While prior studies have examined the safety of LLMs in general usage, code generation, and…

Solving arithmetic tasks is a simple and fundamental skill, yet modern Large Language Models (LLMs) have great difficulty with them. We introduce the Integrated Gated Calculator (IGC), a module that enables LLMs to perform arithmetic by…

Large Language Models (LLMs) are increasingly susceptible to jailbreak attacks, which are adversarial prompts that bypass alignment constraints and induce unauthorized or harmful behaviors. These vulnerabilities undermine the safety,…

As the scale and complexity of jailbreaking attacks on large language models (LLMs) continue to escalate, their efficiency and practical applicability are constrained, posing a profound challenge to LLM security. Jailbreaking techniques…

In-context learning (ICL) effectively conditions large language models (LLMs) for molecular tasks, such as property prediction and molecule captioning, by embedding carefully selected demonstration examples into the input prompt. This…

While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation…

The recent boom and rapid integration of Large Language Models (LLMs) into a wide range of applications warrants a deeper understanding of their security and safety vulnerabilities. This paper presents a comparative analysis of the…