UntrustVul identifies untrustworthy vulnerability predictions by marking lines that neither match historical vulnerability patterns nor influence vulnerable lines through dependencies, reporting AUC 70-88% and F1 82-94% on 115K predictions.
Rittichier, and Arjan Durresi
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
A lifecycle-based survey of LLM fine-tuning security that reviews attacks and defenses by intervention phase and reports unified empirical findings on model-dependent attack effectiveness and limited defense generalization.
Simulations of 1200 interactions show that voting protocol choice and agent deliberation change which response is selected by role-constrained pedagogical agents on SciQ and HumanEval benchmarks, producing distinct coordination patterns and some simulated learning gains.
A survey that maps risks along the agent workflow and consolidates metrics and benchmarks for safety, robustness, privacy, and security in agentic AI.
Generative AI suitability in qualitative research depends primarily on the approach (small-q positivist/post-positivist or Big Q non-positivist) along with skills, ethics, and personal preferences.
citing papers explorer
-
UntrustVul: An Automated Approach for Identifying Untrustworthy Alerts in Vulnerability Detection Models
UntrustVul identifies untrustworthy vulnerability predictions by marking lines that neither match historical vulnerability patterns nor influence vulnerable lines through dependencies, reporting AUC 70-88% and F1 82-94% on 115K predictions.
-
Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions
A lifecycle-based survey of LLM fine-tuning security that reviews attacks and defenses by intervention phase and reports unified empirical findings on model-dependent attack effectiveness and limited defense generalization.
-
Voting Protocols as Coordination Mechanisms for Role-Constrained Multi-Agent Tutoring Systems
Simulations of 1200 interactions show that voting protocol choice and agent deliberation change which response is selected by role-constrained pedagogical agents on SciQ and HumanEval benchmarks, producing distinct coordination patterns and some simulated learning gains.
-
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
A survey that maps risks along the agent workflow and consolidates metrics and benchmarks for safety, robustness, privacy, and security in agentic AI.
-
To Vibe Research or Not to Vibe Research? Generative AI in Qualitative Research
Generative AI suitability in qualitative research depends primarily on the approach (small-q positivist/post-positivist or Big Q non-positivist) along with skills, ethics, and personal preferences.