Related papers: Inhibitory Attacks on Backdoor-based Fingerprintin…
GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite…
Large language models deployed at runtime can misbehave in ways that clean-data validation cannot anticipate: training-time backdoors lie dormant until triggered, jailbreaks subvert safety alignment, and prompt injections override the…
Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal…
Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness…
Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Despite their impressive performance, recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts…
Given the high cost of large language model (LLM) training from scratch, safeguarding LLM intellectual property (IP) has become increasingly crucial. As the standard paradigm for IP ownership verification, LLM fingerprinting thus plays a…
Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…
This paper proposes a jailbreaking prompt detection method for large language models (LLMs) to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts…
The widespread deployment of pre-trained language models (PLMs) has exposed them to textual backdoor attacks, particularly those planted during the pre-training stage. These attacks pose significant risks to high-reliability applications,…
Training large language models (LLMs) is resource-intensive and expensive, making protecting intellectual property (IP) for LLMs crucial. Recently, embedding fingerprints into LLMs has emerged as a prevalent method for establishing model…
Recently, applications powered by Large Language Models (LLMs) have made significant strides in tackling complex tasks. By harnessing the advanced reasoning capabilities and extensive knowledge embedded in LLMs, these applications can…
Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human…
Large Language Model (LLM)-generated data is increasingly used in software analytics, but it is unclear how this data compares to human-written data, particularly when models are exposed to adversarial scenarios. Adversarial attacks can…
This paper presents a systematic security assessment of four prominent Large Language Models (LLMs) against diverse adversarial attack vectors. We evaluate Phi-2, Llama-2-7B-Chat, GPT-3.5-Turbo, and GPT-4 across four distinct attack…
Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generate incorrect outputs in the presence of specific, often…
The safety and robustness of large language models (LLMs) based applications remain critical challenges in artificial intelligence. Among the key threats to these applications are prompt hacking attacks, which can significantly undermine…
Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…
Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL). However, the vulnerability of ICL to privacy…
We introduce LLMmap, a first-generation fingerprinting technique targeted at LLM-integrated applications. LLMmap employs an active fingerprinting approach, sending carefully crafted queries to the application and analyzing the responses to…
Open-source large language models (LLMs) have become increasingly popular among both the general public and industry, as they can be customized, fine-tuned, and freely used. However, some open-source LLMs require approval before usage,…