Hazardous Biological and Chemical Technologies

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Anwar et al. (2024)

Source DOI

Sub-category

Risk Domain

4Malicious Actors & Misuse

4.2Cyberattacks, weapon development or use, and mass harm

Using AI systems to develop cyber weapons (e.g., by coding cheaper, more effective malware), develop new or enhance existing weapons (e.g., Lethal Autonomous Weapons or chemical, biological, radiological, nuclear, and high-yield explosives), or use weapons to cause mass harm.

"AI systems such as LLMs, chemical LLMs (Skinnider et al., 2021; Moret et al., 2023), and other LLM- based biological design tools might soon facilitate the production of bioweapons, chemical weapons, and other hazardous technologies. In particular, LLMs might enable actors with less expertise to more easily synthesize dangerous pathogens, while customized chemical and biological design tools might be more concerning in terms of expanding the capabilities of sophisticated actors (e.g. states) (Sandbrink, 2023). Gopal et al. (2023) and Soice et al. (2023) demonstrated that people with little background could use LLMs to help make progress towards developing pathogens such as the 1918 pandemic influenza. However, recent studies suggest that current LLMs are not more helpful than internet search in this regard (Mouton et al., 2024; Patwardhan et al., 2024)."(p. 87)

Entity— Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Supporting Evidence (1)

"...(future) LLM-based technologies could develop strong reasoning capabilities that might help them make novel discoveries (Romera-Paredes et al., 2024) — this potential to make novel discoveries could also transfer to hazardous chemical and biological technologies (Moret et al., 2023), potentially, resulting in technology designs that might be more challenging to guard against via supply-chain monitoring"(p. 88)

Part of Vulnerability to Poisoning and Backdoors