674 citations · 1.6k across the 88 of their papers we have counts for
96 papers
MLCommons Jailbreak Benchmark v1.0
Carsten Maple, Cagatay Yucel, Isaac Holeman +33
Modern AI systems are designed to refuse hazardous requests. A jailbreak is a prompt crafted to bypass those safeguards and elicit outputs that the system would normally refuse to…
Certified Multi-Source Integrity for Structured Agent Actions
Anmol Pandey, Aditya Jain, Liang Chen +2
LLM agents increasingly take privileged, often irreversible structured actions, such as paying an invoice. They assemble each action from action-critical fields in documents and to…
Probabilistic Robustness-driven Universal Adversarial Perturbations with Explainability against Deep Reinforcement Learning-based Intrusion Detection System
Hongsen Zhang, Lu Zhang, Mingjing Xu +3
Deep reinforcement learning (DRL) enables adaptive intrusion detection in dynamic network environments but also exposes intrusion detection systems (IDS) to adversarial threats suc…
No Time to Collapse: Unlocking Robustness and Multiplexed Capacity in Frozen Audio Watermarkers
Xuanye Wang, Linxi Li, Yechen Wang +3
Modern neural audio watermarking systems typically embed a message repeatedly across time and then collapse the resulting temporal evidence into a single payload using averaging, v…
Empirical Auditing of Edge-Private Graph Generators
Anum Fatima, Stratis Limnios, James Adams +4
We empirically audit privacy leakage by testing whether outputs from edge-neighbouring inputs remain distinguishable, using statistically valid lower bounds on the privacy loss wit…
ETH-TraceBench: A Large-Scale Event-Stream Benchmark for Ethereum DeFi under Temporal, Protocol, and Contract Shift
Kemal Kirtac, Carsten Maple
Ethereum decentralized finance (DeFi) provides a public, time-stamped record of transaction-level event streams, but the same public symbols can create strong machine-learning shor…