Weaponized AI for cyber attacks

Increasing AI cyber-offensive capabilities including those that target other AI systems via adversarial attacks and jailbreaking - without a commensurate increase in defensive capabilities could make this form of conflict cheaper, more widespread, and perhaps also harder to detect.

“Increasing AI cyber-offensive capabilities including those that target other AI systems via adversarial attacks and jailbreaking (Gleave et al., 2020; Yamin et al., 2021; Zou et al., 2023) - without a commensurate increase in defensive capabilities could make this form of conflict cheaper, more widespread, and perhaps also harder to detect (Brundage et al., 2018).”

Researchers have warned about the potential misuse of LLMs to generate mis/disinformation and harmful content.

“researchers have warned about the potential misuse of such technologies to generate mis/disinformation and harmful content (Bommasani et al., 2021;Yamin et al., 2021;Guembe et al., 2022;Goldstein et al., 2023).”

LLMs have the potential to reshape the landscape of cyber-social security dramatically.

“Therefore, LLMs have the potential to reshape the landscape of cyber-social security dramatically, a concern shared by many researchers (Bommasani et al., 2021;Yamin et al., 2021;Guembe et al., 2022;Goldstein et al., 2023;Kucharavy et al., 2023).”