Role Grounding Attack writes attacker preferences into agent memory
Nested social posts make victim agents treat an attacker's preferences as the user's, steering tools and leaking data.
Stories per day · 30 days
2 RSS
Relatedfederated-learning2llm-agents2agent-memory1autonomous-vehicles1backdoor1data-poisoning1fedavg1fltrust1jailbreak1llm-as-judge1mobilenet1persistent-memory1personal-data1privacy1red-teaming1role-grounding1secure-mpc1tool-selection1
6 stories, newest first · one card per story
Stories tagged #privacy-leakage
PrivacyEvalClaw audits privacy leaks in LLM jailbreak replies
The training-free agent gathers evidence and reconciles conflicting judges before scoring indirect or partial personal disclosures.
PPFLex uses MPC to stop federated guidance from leaking labels
In the authors' experiment, a malicious server inferred client label sets from shared guidance matrices at 50% to 84% accuracy.
Persistent memory in LLM agents widens privacy leakage over sessions
Instructing the agent not to state or presuppose attributes cut leakage near the no-memory level while keeping most quality gains.
Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-Tuning
A summer-school study shows federated fine-tuning of MobileNetV4 leaks labels and stays open to client backdoors.
CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents
CIPL evaluates how much sensitive data in LLM-agent pipelines an external attacker can actually recover.