Results 11 to 20 of about 883,375 (392)
Auditing large language models: a three-layered approach [PDF]
AI and Ethics, 2023 Large language models (LLMs) represent a major advance in artificial intelligence (AI) research. However, the widespread use of LLMs is also coupled with significant ethical and social challenges.
Jakob Mokander +3 more
semanticscholar +1 more source
Automatically Auditing Large Language Models via Discrete Optimization [PDF]
International Conference on Machine Learning, 2023 Auditing large language models for unexpected behaviors is critical to preempt catastrophic deployments, yet remains challenging. In this work, we cast auditing as an optimization problem, where we automatically search for input-output pairs that match a
Erik Jones +3 more
semanticscholar +1 more source
Privacy Auditing with One (1) Training Run [PDF]
Neural Information Processing Systems, 2023 We propose a scheme for auditing differentially private machine learning systems with a single training run. This exploits the parallelism of being able to add or remove multiple training examples independently.
T. Steinke +2 more
semanticscholar +1 more source
Supporting Human-AI Collaboration in Auditing LLMs with LLMs [PDF]
AAAI/ACM Conference on AI, Ethics, and Society, 2023 Large language models (LLMs) are increasingly becoming all-powerful and pervasive via deployment in sociotechnical systems. Yet these language models, be it for classification or generation, have been shown to be biased, behave irresponsibly, causing ...
Charvi Rastogi +3 more
semanticscholar +1 more source
Tight Auditing of Differentially Private Machine Learning [PDF]
USENIX Security Symposium, 2023 Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy estimate (nearly) matches the ...
Milad Nasr +7 more
semanticscholar +1 more source
Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem [PDF]
Conference on Fairness, Accountability and Transparency, 2022 Algorithmic audits (or ‘AI audits’) are an increasingly popular mechanism for algorithmic accountability; however, they remain poorly defined. Without a clear understanding of audit practices, let alone widely used standards or regulatory guidance ...
Sasha Costanza-Chock +2 more
semanticscholar +1 more source
Understanding Practices, Challenges, and Opportunities for User-Engaged Algorithm Auditing in Industry Practice [PDF]
International Conference on Human Factors in Computing Systems, 2022 Recent years have seen growing interest among both researchers and practitioners in user-engaged approaches to algorithm auditing, which directly engage users in detecting problematic behaviors in algorithmic systems.
Wesley Hanwen Deng +5 more
semanticscholar +1 more source
144 For Audit's Sake: An Audit of Audits [PDF]
British Journal of Surgery, 2021 Abstract Aim Audit is a mandatory requirement for completion of Dental Core Training. Consequently, many audits undertaken by trainees are to “tick a box”, leading to incomplete or poor-quality audits, with change either not implemented or never measured.
G Dhanjal +3 more
openaire +2 more sources
Everyday Algorithm Auditing: Understanding the Power of Everyday Users in Surfacing Harmful Algorithmic Behaviors [PDF]
Proc. ACM Hum. Comput. Interact., 2021 A growing body of literature has proposed formal approaches to audit algorithmic systems for biased and harmful behaviors. While formal auditing approaches have been greatly impactful, they often suffer major blindspots, with critical issues surfacing ...
Hong Shen +3 more
semanticscholar +1 more source
Closing the AI accountability gap: defining an end-to-end framework for internal algorithmic auditing [PDF]
FAT*, 2020 Rising concern for the societal implications of artificial intelligence systems has inspired a wave of academic and journalistic literature in which deployed systems are audited for harm by investigators from outside the organizations deploying the ...
Inioluwa Deborah Raji +8 more
semanticscholar +1 more source