Current Security Threats in Large Language Model Applications
summary
Overview of current security threats affecting applications that use large language models, covering risks in LLMs themselves and in systems built on them. Discusses attack vectors and vulnerabilities relevant to developers of high-load systems, with focus on practical implications for deploying and securing LLM-based services.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 3:28Injection threats in LLM
- 8:53Model output attacks
- 11:21Training data poisoning
- 14:37LLM denial of service
- 18:42Supply chain attacks
- 21:32Confidential data leaks
- 25:48LLM plugin dangers
- 30:07Over-reliance on LLM
- 33:41Intellectual property risks
- 46:55Q&A
related talks
23mSecurity and auditing tools in Large Language Models (LLM)
31mHacking with Words...
47mA Step-by-Step Guide to Securing Large Language Models (LLMs)
44mI Abuse Your LLM Live with 10 Security Vulnerabilities
46mHow Large Language Models Are Reshaping the Cybersecurity Landscape
40mFrom Text to Flaws: Application Vulnerabilities with Generative AI and LLMs
49mSecuring AI Apps with the OWASP Top Ten for Large Language Models
25mSecuring AI applications by building our own LLM Vulnerability Scanner in Python