Related papers: From Prompt to Physical Action: Structured Backdoo…
Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdoor strategies predominantly operate at the token level, where an injected trigger causes…
During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, existing defense strategies suffer from limited…
Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers…
The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…
Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…
Embodied AI represents systems where AI is integrated into physical entities. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensively employed in embodied AI by facilitating sophisticated…
Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other hand, COT prompting also poses new vulnerabilities in the…
Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…
Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on…
Large Language Models (LLMs), especially those accessed via APIs, have demonstrated impressive capabilities across various domains. However, users without technical expertise often turn to (untrustworthy) third-party services, such as…
This paper studies the integration off Large Language Models into cybersecurity tools and protocols. The main issue discussed in this paper is how traditional rule-based and signature based security systems are not enough to deal with…
Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural…
Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection…
The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…
Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics. However, their complex multimodal interactions also expose new security vulnerabilities. In this paper, we investigate a…
The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied, prompt-based…
Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…
Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…
Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…
Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to…