Access more than 1300+ documented risks, classified by domain, intent, and deployment timing. This database integrates 43 global safety frameworks.
Start from a domain hub, then open representative MIT risks with canonical detail URLs.
Risks of bias, toxicity, discriminatory harm, and systemic exclusion in AI systems.
mit668
Adult content
These evaluations assess if a LLM can generate content that should only be viewed by adults (e.g., sexual material or depictions of sexual activity)
mit485
Adult Content
LLMs have the capability to generate sex-explicit conversations, and erotic texts, and to recommend websites with sexual content
Risks of data leakage, attacks, system compromise, and misuse of sensitive information.
mit1504
“Model Psychology” Attacks
LLMs are vulnerable to “psychological” tricks (Li et al., 2023e; Shen et al., 2023), which can be exploited by attackers. Examples include instructing the model to behave like a specific persona (Shah et al., 2023; Andreas, 2022), or employing various “social engineering” tricks crafted by humans (Wei et al., 2023c) or other LLMs (Perez et al., 2022b; Casper et al., 2023c).
mit381
Adversarial AI (General)
Adversarial AI refers to a class of attacks that exploit vulnerabilities in machine-learning (ML) models. This class of misuse exploits vulnerabilities introduced by the AI assistant itself and is a form of misuse that can enable malicious entities to exploit privacy vulnerabilities and evade the model’s built-in safety mechanisms, policies, and ethical boundaries of the model. Besides the risks of misuse for offensive cyber operations, advanced AI assistants may also represent a new target for abuse, where bad actors exploit the AI systems themselves and use them to cause harm. While our understanding of vulnerabilities in frontier AI models is still an open research problem, commercial firms and researchers have already documented attacks that exploit vulnerabilities that are unique to AI and involve evasion, data poisoning, model replication, and exploiting traditional software flaws to deceive, manipulate, compromise, and render AI systems ineffective. This threat is related to, but distinct from, traditional cyber activities. Unlike traditional cyberattacks that typically are caused by ‘bugs’ or human mistakes in code, adversarial AI attacks are enabled by inherent vulnerabilities in the underlying AI algorithms and how they integrate into existing software ecosystems.
Risks of misleading content, narrative manipulation, and degradation of the information environment.
mit1343
-
AI systems generating and facilitating the spread of inaccurate or misleading information that causes people to develop false beliefs
mit900
AI contributes to increased online polarisation
One of the most significant commercial uses of current AI systems is in the content recommendation algorithms of social media companies, and there are already concerns that this is contributing to worsened polarisation online
Risks created by deliberate malicious use of AI tools and capabilities.
Risks at the human-system interface, including dependence, deception, and erosion of agency.
mit1336
-
Loss of or restrictions to the ability or rights of an individual, group or entity to make decisions and control their identity and/or output due to the use of misuse of a technology system or set of systems
mit946
Addiction
Addiction - Emotional or material dependence on technology or a technology system.
Distributional, institutional, and environmental risks created by AI deployment.
mit1045
Ability to automate jobs
The ability to automate jobs by AI models and systems can lead to significant job displacement, economic disruption, and social inequality.
mit629
Accelerated development of nanotechnology produces uncontrolled production of toxic nanoparticles
AI is a key component for the development of nanobots, which could have dangerous environmental implications by invisibly modifying substances at nanoscale. For example, nanobots could start chemical reactions that would create invisible nanoparticles that are toxic and potentially lethal.
Risks of failures, unsafe behavior, and operational limits in AI systems and models.
mit562
Access to Increased Resources
Future AI systems may gain access to websites and engage in real-world actions, potentially yielding a more substantial impact on the world (Nakano et al., 2021). They may disseminate false information, deceive users, disrupt network security, and, in more dire scenarios, be compromised by malicious actors for ill purposes. Moreover, their increased access to data and resources can facilitate self-proliferation, posing existential risks (Shevlane et al., 2023).
mit1452
Accident Risks
Risks arising from operational failures, model misjudgments, or improper human operation of AI systems deployed in safety-critical infrastructure, where single points of failure can trigger cascading catastrophic consequences.