Related papers: Language Models Can Autonomously Hack and Self-Rep…
In recent years, large language models (LLMs) have become increasingly capable and can now interact with tools (i.e., call functions), read documents, and recursively call themselves. As a result, these LLMs can now function autonomously as…
Uncontrollable autonomous replication of language model agents poses a critical safety risk. To better understand this risk, we introduce RepliBench, a suite of evaluations designed to measure autonomous replication capabilities. RepliBench…
Recent research has demonstrated the potential of Large Language Models (LLMs) for autonomous penetration testing, particularly when using cloud-based restricted-weight models. However, reliance on such models introduces security, privacy,…
Large language models (LLMs) have significantly influenced various industries but suffer from a critical flaw, the potential sensitivity of generating harmful content, which poses severe societal risks. We developed and tested novel attack…
LLMs have becoming increasingly powerful, both in their benign and malicious uses. With the increase in capabilities, researchers have been increasingly interested in their ability to exploit cybersecurity vulnerabilities. In particular,…
Generative artificial intelligence, and large language models in particular, have emerged as one of the most transformative paradigms in modern computer science. This automated survey provides an accessible treatment of the field as of…
Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, real-world APIs are often more flexible than just text…
Large language models (LLMs) have seen widespread applications across various domains, yet remain vulnerable to adversarial prompt injections. While most existing research on jailbreak attacks and hallucination phenomena has focused…
Large language models (LLMs), especially generative pre-trained transformers (GPTs), have recently demonstrated outstanding ability in information comprehension and problem-solving. This has motivated many studies in applying LLMs to…
The large transformer-based language models demonstrate excellent performance in natural language processing. By considering the transferability of the knowledge gained by these models in one domain to other related domains, and the…
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…
Large Language Models (LLMs) have demonstrated remarkable capabilities in code-related tasks, raising concerns about their potential for automated exploit generation (AEG). This paper presents the first systematic study on LLMs'…
Ensuring the security of large language models (LLMs) is an ongoing challenge despite their widespread popularity. Developers work to enhance LLMs security, but vulnerabilities persist, even in advanced versions like GPT-4. Attackers…
Language models typically need to be trained or finetuned in order to acquire new knowledge, which involves updating their weights. We instead envision language models that can simply read and memorize new data at inference time, thus…
Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…
Large language models have gained significant popularity because of their ability to generate human-like text and potential applications in various fields, such as Software Engineering. Large language models for code are commonly trained on…
Previous learning-based vulnerability detection methods relied on either medium-sized pre-trained models or smaller neural networks from scratch. Recent advancements in Large Pre-Trained Language Models (LLMs) have showcased remarkable…
Deep learning models for drug-like molecules and proteins overwhelmingly reuse transformer architectures designed for natural language, yet whether molecular sequences benefit from different designs has not been systematically tested. We…
Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks work either in the white-box setting (with full access to the…
A major risk of using language models in practical applications is their tendency to hallucinate incorrect statements. Hallucinations are often attributed to knowledge gaps in LMs, but we hypothesize that in some cases, when justifying…