Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and
Vulnerabilities
- URL: http://arxiv.org/abs/2308.12833v1
- Date: Thu, 24 Aug 2023 14:45:50 GMT
- Title: Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and
Vulnerabilities
- Authors: Maximilian Mozes, Xuanli He, Bennett Kleinberg, Lewis D. Griffin
- Abstract summary: Large language models (LLMs) can be misused for fraud, impersonation, and the generation of malware.
We present a taxonomy describing the relationship between threats caused by the generative capabilities of LLMs, prevention measures intended to address such threats, and vulnerabilities arising from imperfect prevention measures.
- Score: 14.684194175806203
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Spurred by the recent rapid increase in the development and distribution of
large language models (LLMs) across industry and academia, much recent work has
drawn attention to safety- and security-related threats and vulnerabilities of
LLMs, including in the context of potentially criminal activities.
Specifically, it has been shown that LLMs can be misused for fraud,
impersonation, and the generation of malware; while other authors have
considered the more general problem of AI alignment. It is important that
developers and practitioners alike are aware of security-related problems with
such models. In this paper, we provide an overview of existing - predominantly
scientific - efforts on identifying and mitigating threats and vulnerabilities
arising from LLMs. We present a taxonomy describing the relationship between
threats caused by the generative capabilities of LLMs, prevention measures
intended to address such threats, and vulnerabilities arising from imperfect
prevention measures. With our work, we hope to raise awareness of the
limitations of LLMs in light of such security concerns, among both experienced
developers and novel users of such technologies.
Related papers
- Global Challenge for Safe and Secure LLMs Track 1 [57.08717321907755]
The Global Challenge for Safe and Secure Large Language Models (LLMs) is a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme Office (CRPO)
This paper introduces the Global Challenge for Safe and Secure Large Language Models (LLMs), a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme Office (CRPO) to foster the development of advanced defense mechanisms against automated jailbreaking attacks.
arXiv Detail & Related papers (2024-11-21T08:20:31Z) - The potential of LLM-generated reports in DevSecOps [3.4888132404740797]
Alert fatigue is a common issue faced by software teams using the DevSecOps paradigm.
This paper explores the potential of LLMs in generating actionable security reports.
Integrating these reports into DevSecOps can mitigate attention saturation and alert fatigue.
arXiv Detail & Related papers (2024-10-02T18:01:12Z) - Recent Advances in Attack and Defense Approaches of Large Language Models [27.271665614205034]
Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities.
Their widespread deployment has raised significant safety and reliability concerns.
This paper reviews current research on LLM vulnerabilities and threats, and evaluates the effectiveness of contemporary defense mechanisms.
arXiv Detail & Related papers (2024-09-05T06:31:37Z) - AI Safety in Generative AI Large Language Models: A Survey [14.737084887928408]
Large Language Model (LLMs) that exhibit generative AI capabilities are facing accelerated adoption and innovation.
Generative AI (GAI) inevitably raises concerns about the risks and safety associated with these models.
This article provides an up-to-date survey of recent trends in AI safety research of GAI-LLMs from a computer scientist's perspective.
arXiv Detail & Related papers (2024-07-06T09:00:18Z) - Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress.
Our investigation exposes a critical oversight in this belief.
By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
arXiv Detail & Related papers (2024-04-16T13:22:54Z) - Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices [4.927763944523323]
Large language models (LLMs) have significantly transformed the landscape of Natural Language Processing (NLP)
This research paper thoroughly investigates security and privacy concerns related to LLMs from five thematic perspectives.
The paper recommends promising avenues for future research to enhance the security and risk management of LLMs.
arXiv Detail & Related papers (2024-03-19T07:10:58Z) - The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative [55.08395463562242]
Multimodal Large Language Models (MLLMs) are constantly defining the new boundary of Artificial General Intelligence (AGI)
Our paper explores a novel vulnerability in MLLM societies - the indirect propagation of malicious content.
arXiv Detail & Related papers (2024-02-20T23:08:21Z) - Prioritizing Safeguarding Over Autonomy: Risks of LLM Agents for Science [65.77763092833348]
Intelligent agents powered by large language models (LLMs) have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines.
While their capabilities are promising, these agents also introduce novel vulnerabilities that demand careful consideration for safety.
This paper conducts a thorough examination of vulnerabilities in LLM-based agents within scientific domains, shedding light on potential risks associated with their misuse and emphasizing the need for safety measures.
arXiv Detail & Related papers (2024-02-06T18:54:07Z) - Privacy in Large Language Models: Attacks, Defenses and Future Directions [84.73301039987128]
We analyze the current privacy attacks targeting large language models (LLMs) and categorize them according to the adversary's assumed capabilities.
We present a detailed overview of prominent defense strategies that have been developed to counter these privacy attacks.
arXiv Detail & Related papers (2023-10-16T13:23:54Z) - Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard
Security Attacks [67.86285142381644]
Recent advances in instruction-following large language models amplify the dual-use risks for malicious purposes.
Dual-use is difficult to prevent as instruction-following capabilities now enable standard attacks from computer security.
We show that instruction-following LLMs can produce targeted malicious content, including hate speech and scams.
arXiv Detail & Related papers (2023-02-11T15:57:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.