Introduces MM-Privacy dataset and evaluations showing MLLMs leak sensitive data from images in various tasks, highlighting task inconsistency effects.
Flocks of Stochastic Parrots: Dif- ferentially Private Prompt Learning for Large Language Models.CoRR abs/2305.15594
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
CSLR aligns unordered private replay lists from clients using public anchor sentence signatures, yielding 3.9-5.6 point gains on continual NLP tasks at ε=4 over non-CSLR DP baselines.
PopQuiz Attack infers LLM training data membership by turning examples into quiz questions and measuring answer accuracy, reaching 0.873 average ROC-AUC across six models and outperforming prior methods by 20.6%.
citing papers explorer
-
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges
Introduces MM-Privacy dataset and evaluations showing MLLMs leak sensitive data from images in various tasks, highlighting task inconsistency effects.
-
Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings
CSLR aligns unordered private replay lists from clients using public anchor sentence signatures, yielding 3.9-5.6 point gains on continual NLP tasks at ε=4 over non-CSLR DP baselines.
-
Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models
PopQuiz Attack infers LLM training data membership by turning examples into quiz questions and measuring answer accuracy, reaching 0.873 average ROC-AUC across six models and outperforming prior methods by 20.6%.