arXiv Machine Learning By Yiting Hu, Lingjie Duan

Theory of Continual Learning Against Data Poisoning Attacks

Read the original on arXiv Machine Learning →

arXiv:2606. 29841v1 Announce Type: new Abstract: Continual learning (CL), where a model is trained on a sequence of data tasks, is increasingly being adopted across key fields such as large language models and image recognition, yet it remains highly vulnerable to data poisoning that triggers learning divergence or severe excess risk.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Jun 29

Theory of Continual Learning Against Data Poisoning Attacks

Continual learning (CL), where a model is trained on a sequence of data tasks, is increasingly being adopted across key fields such as large language models and image recognition, yet it remains highly vulnerable to data poisoning that triggers learning divergence or severe excess risk. Despite these threats, a principled theoretical foundation in CL for understanding attack and defense remains lacking.

Hugging Face Trending Papers
Jun 13

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment

Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense.

arXiv AI
Jun 3

Inference Cost Attacks for Retrieval-Augmented Large Language Models

arXiv:2606. 02643v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG)-enhanced LLM systems, while powerful, introduce substantial inference costs due to the inclusion of an extra multi-stage pipeline that dynamically retrieves and synthesizes information from external knowledge sources.

By Chengliang Liu, Liangbo Ning, Yujuan Ding, Wenqi Fan