MIT AI Risk Repository · domain 4: Malicious actors
4.2 Cyberattacks, weapon development or use, and mass harm
Using AI systems to develop cyber weapons (e.g., coding cheaper, more effective malware), develop new or enhance existing weapons (e.g., Lethal Autonomous Weapons or CBRNE), or use weapons to cause mass harm.
- 82
- 12
- 15
- 14
| Label | Value |
|---|---|
| Human | 61 |
| AI | 11 |
| Other | 8 |
| Not coded | 2 |
| Label | Value |
|---|---|
| Intentional | 68 |
| Other | 10 |
| Unintentional | 2 |
| Not coded | 2 |
| Label | Value |
|---|---|
| Post-deployment | 71 |
| Other | 7 |
| Pre-deployment | 2 |
| Not coded | 2 |
| Label | Value |
|---|---|
| 2017 | 1 |
| 2020 | 1 |
| 2022 | 1 |
| 2023 | 1 |
| 2024 | 2 |
| 2025 | 9 |
| Label | Value |
|---|---|
| Risk Category | 16 |
| Risk Sub-Category | 66 |
Risk entries
Browse and export all- Acquisition of a goal to harm society
"cases of AI systems being given the outright goal of harming humanity (ChaosGPT);"
- Failures in or misuse of intermediary (non-AGI) AI systems, resulting in catastrophe
"Deployment of “prepotent” AI systems that are non-general but capable of outperforming human collective efforts on various key dimensions;170 → Militarization of AI enabling mass attacks using swarms...
- Biosecurity Threats
"The potential misuse of general purpose AI models also extends to biosecurity threats. Biological weapons are generally understood as biological toxins or infectious agents such as viruses that are i...
- Model diversion
"Model Diversion takes model manipulation one step further, by repurposing (often open-source) generative AI models in a way that diverts them from their intended functionality or from the use cases e...
- Unauthorized manipulation of AI
"AI machines could be hacked and misused, e.g. manipulating an airport luggage screening system to smuggle weapons"
- CBRN Information or Capabilities
"Eased access to or synthesis of materially nefarious information or design capabilities related to chemical, biological, radiological, or nuclear (CBRN) weapons or other dangerous materials or agent...
- Information Security
"Lowered barriers for offensive cyber capabilities, including via automated discovery and exploitation of vulnerabilities to ease hacking, malware, phishing, offensive cyber operations, or other cyber...
- Purposeful or malicious harm
"EAI systems present distinct physical risks due to their embodiment in the physical world. EAI technologies have already been designed and deployed with lethal intent, such as AI-controlled drones [5...
- Abuse & Misuse
"The potential for AI systems to be used maliciously or irresponsibly, including for creating deepfakes, automated cyber attacks, or invasive surveillance systems. Specifically denotes intentional use...
- Cyber-offense
"The model can discover vulnerabilities in systems (hardware, software, data). It can write code for exploiting those vulnerabilities. It can make effective decisions once it has gained access to a sy...
- Chemical Risks
"Chemical risks involve the exploitation of agents to synthesize chemical weapons, as well as the creation or release of hazardous substances during autonomous chemical experiments. This category also...
- Biological Risks
"Biological risks encompass the dangerous modification of pathogens and unethical manipulation of genetic material, potentially leading to unforeseen biohazardous outcomes."
- Cyberspace risks (Risks of abuse for cyberattacks)
"AI can be used in launching automatic cyberattacks or increasing attack efficiency, including exploring and making use of vulnerabilities, cracking passwords, generating malicious codes, sending phis...
- Real-world risks (Risks of misuse of dual-use items and technologies)
"Due to improper use or abuse, AI can pose serious risks to national security, economic security, and public health security, such as greatly reducing the capability requirements for non-experts to de...
- Security
"Implications of the weaponization of AI for defence (the embeddedness of AI-based capabilities across the land, air, naval and space domains may affect combined arms operations)."
- Cyber Offense Risks
"AI-enabled cyber offense poses a significant cyber domain security risk by fundamentally transforming the scale, sophistication, and accessibility of cyber-attacks. Unlike traditional cyber threats,...
- Biological and Chemical Risks
"The dual-use nature of AI technology presents a critical risk by significantly lowering technical thresholds for malicious non-state actors to design, synthesize, acquire, and deploy CBRNE (Chemical,...
- Physical Harm and Injury Risks
"The integration of general-purpose AI models into embodied systems creates direct physical threats through malicious exploitation of autonomous decision-making capabilities in real-world environments...
- Warfare
"The dangers of AI amplifying the effectiveness/failures of nuclear, chemical, biological, and radiological weapons."
- Ability to enhance and modify pathogens
"AI can be used to enhance pathogens, making them more lethal or resistant to treatments."
- Terrorist access
"Powerful AI technologies may fall into the hands of terrorists."
- Weaponization capabilities
"AI capabilities that could be deliberately weaponized for destructive purposes."
- Indiscriminate weapons (CBRNE)
"This category addresses responses that enable, encourage, or endorse the creation of indiscriminate weapons (colloquially known as "weapons of mass destruction")."
- Assisting code generation for cyber attacks, weapons, or malicious use
- Assisting code generation for cyber security threats
Anticipated risk: "Creators of the assistive coding tool Co-Pilot based on GPT-3 suggest that such tools may lower the cost of developing polymorphic malware which is able to change its features in or...