On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “Vulnerability-Aware”

Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamicscs.LG

New method defends RL agents from poisoning attacks without MDP knowledge.

problem Poisoning attacks on RL systems can cause learning failures.

method Generic poisoning framework for online RL, Vulnerability-Aware Adversarial Critic Poison (VA2C-P).

result Successfully prevents RL agents from learning good policies or converging to target policies.

Reinforcement Learning Poisoning Attacks Vulnerability-Aware Adversarial Critic Stability Radius

2020-09-02abs ↗pdf ↗

Are Targeted Data Poisoning Attacks as Effective as We Think?cs.LG

This paper evaluates targeted data poisoning attacks by focusing on the hardest samples, improving evaluation and defense strategies.

problem The effectiveness of targeted data poisoning attacks is often overestimated due to average evaluation methods.

method The paper introduces metrics to identify the hardest and easiest to poison samples based on clean model information.

result The proposed metrics reliably stratify samples by poisoning vulnerability, enabling rigorous worst-case evaluation and proactive defense.

data poisoning targeted attacks evaluation methods poison vulnerability proactive defense

2025-09-08abs ↗pdf ↗