MIT AI Risk Repository
Browse AI risks
82 risk entries extracted from 74 frameworks, coded by domain, subdomain, causal entity, intent and timing. Filter, then export the current selection with its licence and citation attached.
-
"Violence/armed conflict - Use or misuse of a technology system to incite, facilitate or conduct cyberattacks, security breaches, lethal, biological and chemical weapons development, resulting in violence and armed conflict."
-
"Attackers are beginning to use general- purpose AI for offensive cyber operations, presenting growing but currently limited risks. Current systems have demonstrated capabilities in low- and medium- complexity cybersecurity tasks, with state- sponsored threat actors actively exploring AI to survey target systems. Malicious actors of varying skill levels can leverage these capabilities against people, organisations, and critical infrastructure such as power grids."
-
"Growing evidence shows general- purpose AI advances beneficial to science while also lowering some barriers to chemical and biological weapons development for both novices and experts. New language models can generate step- by- step technical instructions for creating pathogens and toxins that surpass plans written by experts with a PhD and surface information that experts struggle to find online, though their practical utility for novices remains uncertain. Other models demonstrate capabilities in engineering enhanced proteins and analysing which candidate pathogens or toxins are most harmfu
-
"The dangers of AI amplifying the effectiveness/failures of nuclear, chemical, biological, and radiological weapons."
-
61.02.02 · Risk Sub-Category
Sources of systemic risks from general-purpose AI
Ability to enhance and modify pathogens
"AI can be used to enhance pathogens, making them more lethal or resistant to treatments."
-
"Powerful AI technologies may fall into the hands of terrorists."
-
61.02.48 · Risk Sub-Category
Sources of systemic risks from general-purpose AI
Weaponization capabilities
"AI capabilities that could be deliberately weaponized for destructive purposes."
-
62.07.05 · Risk Sub-Category
Direct Harm Domains (system and operational)
Operational harms (autonomous weapons)
—
-
62.08.06 · Risk Sub-Category
Direct Harm Domains (content safety harms)
Dangerous content (e.g., CBRN)
—
-
62.15.05 · Risk Sub-Category
Fine-tuning related (Harmful fine-tuning of open-weights models)
"Models with publicly available weights can be fine-tuned for harmful activities by bad actors, using significantly fewer resources (in terms of time and money) compared to the original training cost [115, 78]."
-
62.30.02 · Risk Sub-Category
AI-based tools attacking critical infrastructure
"Critical infrastructure can also be damaged without AI integration, for instance, when AI-based tools are used indirectly to aid actions such as in coordinated power outages caused by large-scale user manipulation [159]."
-
"AI systems embedded with systemic biases can manipulate large population segments, particularly when these biases align with the beliefs or behaviors of the targeted group. When weaponized at scale, this manipulation can exacerbate social divisions or cause large-scale disruptions, such as city-wide blackouts (e.g., by the manipulation of power consumption into the peak demand period [159])."
-
62.32.00 · Risk Category
-
-
62.32.01 · Risk Sub-Category
Automated discovery and exploitation of software systems
"GPAIs can be used to aid in the automated discovery of software vulnerabilities [33]. This can empower malicious actors, making their cyberattacks more effi- cient and potentially more damaging. This type of automation allows attackers to expand the scale of their operations at a low cost, increasing the impact of their actions. New malware can be developed automatically, or the known vulnerabilities can be exploited to create more sophisticated attacks."
-
"General-purpose AI models may significantly enhance the magnitude and ef- fectiveness of cyberattacks, by amplifying existing capabilities or resources of malicious actors [3]. For example, GPAI models may be employed to: • Automatically scan open-source codebases and compiled binaries for po- tential vulnerabilities • Apply known exploits flexibly and at scale (e.g., identifying vulnerable computers based on subtle cues in response times or output formats) • Assist with different aspects of cyberattacks, including planning, recon- naissance, exploit searching, remote control, malware impleme
-
62.33.00 · Risk Category
-
-
62.33.01 · Risk Sub-Category
Misuse of AI systems to assist in the creation of weapons
"AI systems may be misused to aid in the creation of weapons, such as chemical, biological, radiological, and nuclear (CBRN) weapons, or augment the abilities of existing weapons, such as providing autonomous capabilities to unmanned weapon systems. Current systems do not significantly aid a malicious actor in these tasks, but they do show early signs [117]. This risk can sometimes be mitigated with input and output filtering, but is still susceptible to adversarial techniques (such as jailbreaking or paraphrasing)."
-
"Models used for drug discovery, such as drug-target affinity prediction models, can be used to identify or develop dangerous toxins. This is particularly concern- ing if the training data contains information related to potentially dangerous proteins and viruses."
-
64.04.04 · Risk Sub-Category
Misuse tactics to compromise GenAI systems (Model integrity)
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 envisioned by their developers (Lin et al., 2024). An example of this is training the BERT open source model on the DarkWeb to create DarkBert.7"
-
"Generative AI facilitating the damage, disruption or destruction of a third-party system and/or its components via malfunction, cyberattacks, etc"
-
"Frontier AI systems have the potential to accelerate advances in the life sciences, from training new scientists to enabling faster scientific workflows. While these capabilities will have tremendous beneficial applications, there is a risk that they can be used for malicious purposes, such as for the development of biological or chemical weapons."
-
"As the programming abilities of AI systems continue to expand, frontier AI is likely to significantly exacerbate existing cyber risks. Most notably, AI systems can be used by potentially anyone to create faster paced, more effective and larger scale cyber intrusion via tailored phishing methods or replicating malware. Frontier AI’s effect on the overall balance between cyber offence and defence is uncertain, as these tools also have many applications in improving the cybersecurity of systems and defenders are mobilising significant resources to utilise frontier AI for defensive purposes.209 I
-
"Chemical, biological, radiological, and nuclear (CBRN) risks are broad classes of threats that have the potential to cause harm to a large number of people. Explosives are also sometimes included in this category, often referred to as CBRNE...The key characteristic of CBRN risk is that it stems from misuse of capable models with a direct pathway to harm, where a malicious actor is able to carry out consequential attacks more efficiently and effectively with the help of AI."
-
68.02.00 · Risk Category
"Cyber risks, especially in the context of cyber offense, are an existing threat that may be exacerbated by AI. [108] demonstrated that teams of LLM agents can exploit zero-day vulnerabilities when given a description of the vulnerability and toy capture-the-flag problems. While cyber risks are not typically regarded as catastrophic, [3] argues that cyberwarfare is an underappreciated risk that poses a credible threat of catastrophic 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 [52, 53]. However, fully autonomous military robots, often integrated with bespoke AI architectures [54, 55], are not yet widely used in combat. While highly or fully autonomous warfare is distinctly possible in the future [56], immediate risks arise from commercially available EAI systems, including AI-controlled quadrupeds and autonomous driving assistants."
-
"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 includes the risks arising from the use of advanced materials, such as nanomaterials, which may have unknown or unpredictable chemical properties."
-
"Biological risks encompass the dangerous modification of pathogens and unethical manipulation of genetic material, potentially leading to unforeseen biohazardous outcomes."
-
"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, AI enables both the automation of existing attack vectors and the creation of entirely new categories of offensive capabilities that can adapt and evolve in real-time. AI can automate and enhance cyber-attacks, including vulnerability discovery and exploitation, password cracking, malicious code generation, sophisticated phishing, network scanning, and social engineering. This could dramatically l
-
"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, Biological, Radiological, Nuclear, and Explosive) weapons. This capability poses unprecedented challenges to national security, international non-proliferation regimes, and global security governance."
-
"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. The risk lies in embodied models' capacity for autonomous action and real-world interaction, and when these capabilities are maliciously exploited they may trigger a series of serious consequences.18"
-
73.03.04 · Risk Sub-Category
Dual-Use Capabilities Enable Malicious Use and Misuse of LLMs
Warfare and Physical Harm
"The use of AI in warfare is highly alarming and may pose dangers to human safety (Hendrycks et al., 2023). Autonomous drone warfare is being aggressively pursued as a tactic in the current war in Ukraine (Meaker, 2023), and may already have been used on human targets (Hambling, 2023). The use of AI- based facial recognition has been documented in the targeting of Palestinians in Gaza (International, 2023). LLMs have already been productized in limited ways for the purposes of warfare planning (Tarantola, 2023). Furthermore, active research is being carried out to develop multimodal-LLMs that
-
73.03.05 · Risk Sub-Category
Dual-Use Capabilities Enable Malicious Use and Misuse of LLMs
Hazardous Biological and Chemical Technologies
"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 ba
Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.