REVIEW 8 cited by
AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies
read the original abstract
We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a significant step towards establishing a unified language for generative AI safety evaluation. We identify 314 unique risk categories organized into a four-tiered taxonomy. At the highest level, this taxonomy encompasses System & Operational Risks, Content Safety Risks, Societal Risks, and Legal & Rights Risks. The taxonomy establishes connections between various descriptions and approaches to risk, highlighting the overlaps and discrepancies between public and private sector conceptions of risk. By providing this unified framework, we aim to advance AI safety through information sharing across sectors and the promotion of best practices in risk mitigation for generative AI models and systems.
Forward citations
Cited by 8 Pith papers
-
KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural Risks
KSAFE-MM is a two-part multimodal safety benchmark for Korean contexts that shows MLLMs are more vulnerable to culturally grounded jailbreaks than generic ones, with a noted safety-over-refusal trade-off.
-
No Safe Dose: How Training Data Drives Unsafe Image Generation
Proportion of unsafe images in training data directly increases unsafe outputs in text-to-image models, independent of absolute count, with complementary risk reduction from safer text encoders.
-
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
EvoSynth evolves code-based jailbreak algorithms via multi-agent self-correction, reaching 85.5% ASR on Claude-Sonnet-4.5 and 95.9% average across targets with greater diversity.
-
Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFT
A task vector from an English guard model transfers safety classification to Korean, Chinese, and Japanese models, and a prefix-SFT variant maintains accuracy under streaming with a single-token classifier.
-
A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents
Analysis of 499 generative AI incidents shows use-related failures predominate and frequently harm non-users, producing a distinct risk profile from traditional AI.
-
Brainrot: Deskilling and Addiction are Overlooked AI Risks
AI safety literature overlooks cognitive deskilling and addiction risks from generative AI despite public concern about them.
-
LLM Harms: A Taxonomy and Discussion
Proposes a five-bucket taxonomy of LLM harms and calls for dynamic auditing, but the systematic review behind it is not reproducible and contains mismatched citations.
-
LLM Harms: A Taxonomy and Discussion
This paper proposes a taxonomy of LLM harms in five categories and suggests mitigation strategies plus a dynamic auditing system for responsible development.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.