This page is still being polished. If you have thoughts, please share them via the feedback form.
Data on this page is preliminary and may change. Please do not share or cite these figures publicly.
Cannot be confidently classified due to insufficient information, excessive vagueness, or ambiguity.
Reasoning
Mitigation name "Misuse" lacks definition and evidence; insufficient information to identify focal activity or mechanism.
Mitigations for weaponized misuse
99.9 OtherMitigation methods for the spread of misinformation
Addressing the spread of LLM-generated misinformation requires a dual approach: first, by detecting the source of the text, i.e., whether it is manually authored or machine-generated; and second, by verifying whether the generated content is factual.
1.2.5 Provenance & WatermarkingMethods for mitigating deepfakes
As deepfake technology becomes more accessible and tools become easier to use, the potential for fraudulent activities, blackmail, and identity theft has grown exponentially. Today, the quality of deepfakes has reached a point where even experienced observers struggle to distinguish between genuine footage and manipulated media. As a result, the very authenticity of digital content is under siege, raising urgent questions about the future of trust in online information. While there have been efforts to develop technical defenses against deepfakes, such as adding defenses (e.g., adversarial noise) to photos posted online to make them unreadable by AI, these measures have proven largely empirically ineffective. Every type of defense has been bypassed by attacks, hence there is no perfect technical solution to counter this (Segerie, 2024). Therefore, to counter the growing threat of deepfake-related crimes, the primary solution is to establish stricter norms and stronger supervision.
3.1.2 Regulatory BodiesValue Misalignment
99.9 OtherValue Misalignment > Mitigating social bias
1 AI SystemValue Misalignment > Privacy protection
1 AI SystemValue Misalignment > Methods for mitigating toxicity
1 AI SystemValue Misalignment > Methods for mitigating LLM amorality
1 AI SystemRobustness to attack
1 AI SystemLarge Language Model Safety: A Holistic Survey
Shi, Dan; Shen, Tianhao; Huang, Yufei; Li, Zhigen; Leng, Yongqi; Jin, Renren; Liu, Chuang; Wu, Xinwei; Guo, Zishan; Yu, Linhao; Shi, Ling; Jiang, Bojian; Xiong, Deyi (2024)
The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing integration of these models into critical applications raises substantial safety concerns, necessitating a thorough examination of their potential risks and associated mitigation strategies. This survey provides a comprehensive overview of the current landscape of LLM safety, covering four major categories: value misalignment, robustness to adversarial attacks, misuse, and autonomous AI risks. In addition to the comprehensive review of the mitigation methodologies and evaluation resources on these four aspects, we further explore four topics related to LLM safety: the safety implications of LLM agents, the role of interpretability in enhancing LLM safety, the technology roadmaps proposed and abided by a list of AI companies and institutes for LLM safety, and AI governance aimed at LLM safety with discussions on international cooperation, policy proposals, and prospective regulatory directions. Our findings underscore the necessity for a proactive, multifaceted approach to LLM safety, emphasizing the integration of technical solutions, ethical considerations, and robust governance frameworks. This survey is intended to serve as a foundational resource for academy researchers, industry practitioners, and policymakers, offering insights into the challenges and opportunities associated with the safe integration of LLMs into society. Ultimately, it seeks to contribute to the safe and beneficial development of LLMs, aligning with the overarching goal of harnessing AI for societal advancement and well-being. A curated list of related papers has been publicly available at https://github.com/tjunlp-lab/Awesome-LLM-Safety-Papers.
Unable to classify
Could not be classified to a specific lifecycle stage
Unable to classify
Could not be classified to a specific actor type
Unable to classify
Could not be classified to a specific AIRM function
Primary
4 Malicious Actors & Misuse