Generative AI is the New Attack Vector for Platforms, According to ActiveFence Threat Intelligence
NEW YORK, May 23, 2023 /PRNewswire/ -- ActiveFence, whose mission is to protect online platforms and their users from malicious behavior and harmful content, today released the "Generative AI: The New Attack Vector for Platforms" report. Through this research, ActiveFence investigated hidden communities to examine how threat actors are abusing generative AI to carry out child sex abuse material (CSAM), disinformation, fraud and extremism.
- Through this research, ActiveFence investigated hidden communities to examine how threat actors are abusing generative AI to carry out child sex abuse material (CSAM), disinformation, fraud and extremism.
- "The explosion of generative AI has far-reaching implications for all corners of the internet," said Noam Schwartz, CEO and founder of ActiveFence.
- Second, these same actors are exploring ways to exploit generative AI, manipulating these models and revealing their inherent vulnerabilities.
- To demonstrate how threat actors manipulate generative AI chatbots for malicious purposes, ActiveFence detected methods used to override several policies of major generative AI platforms.