Related papers: Target-driven Attack for Large Language Models
Large language models (LLMs) increasingly employ guardrails to enforce ethical, legal, and application-specific constraints on their outputs. While effective at mitigating harmful responses, these guardrails introduce a new class of…
With the burgeoning advancements in the field of natural language processing (NLP), the demand for training data has increased significantly. To save costs, it has become common for users and businesses to outsource the labor-intensive task…
Large Vision-Language Models (LVLMs) are foundational to modern multimodal applications, yet their susceptibility to adversarial attacks remains a critical concern. Prior white-box attacks rarely generalize across tasks, and black-box…
Large Language Models (LLMs) have achieved remarkable success but remain highly susceptible to jailbreak attacks, in which adversarial prompts coerce models into generating harmful, unethical, or policy-violating outputs. Such attacks pose…
Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become…
Information security is facing increasingly severe challenges, and traditional protection means are difficult to cope with complex and changing threats. In recent years, as an emerging intelligent technology, large language models (LLMs)…
Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced the naturalness and flexibility of human computer interaction by enabling seamless understanding across text, vision, and audio modalities. Among these,…
Deep learning has demonstrated state-of-the-art performance for a variety of challenging computer vision tasks. On one hand, this has enabled deep visual models to pave the way for a plethora of critical applications like disease…
Large Language Models (LLMs) have been widely adopted to enhance Task-Oriented Dialogue Systems (TODS) by modeling complex language patterns and delivering contextually appropriate responses. However, this integration introduces significant…
Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that…
Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers. However, in the black-box setting, the attacker is limited only to the query…
Large Language Model (LLM) jailbreak refers to a type of attack aimed to bypass the safeguard of an LLM to generate contents that are inconsistent with the safe usage guidelines. Based on the insights from the self-attention computation…
Large Language Models (LLMs) have recently demonstrated impressive capabilities across various real-world applications. However, due to the current text-in-text-out paradigm, it remains challenging for LLMs to handle dynamic and complex…
Recent advances confirm that large language models (LLMs) can achieve state-of-the-art performance across various tasks. However, due to the resource-intensive nature of training LLMs from scratch, it is urgent and crucial to protect the…
Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…
Large language models (LLMs) are susceptible to social-engineered attacks that are human-interpretable but require a high level of comprehension for LLMs to counteract. Existing defensive measures can only mitigate less than half of these…
Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, prompting interest in their application as black-box optimizers. This paper asserts that LLMs possess the capability for zero-shot optimization across diverse…
Textual data is often represented as real-numbered embeddings in NLP, particularly with the popularity of large language models (LLMs) and Embeddings as a Service (EaaS). However, storing sensitive information as embeddings can be…
Recent researches have shown that Large Language Models (LLMs) are susceptible to a security threat known as Backdoor Attack. The backdoored model will behave well in normal cases but exhibit malicious behaviours on inputs inserted with a…
Meta-black-box optimization has been significantly advanced through the use of large language models (LLMs), yet in fancy on constrained evolutionary optimization. In this work, AwesomeDE is proposed that leverages LLMs as the strategy of…