4 papers
(A)iSpy: Parasitic Trojans for Machine Learning Infrastructure
Habibur Rahaman, Qipan Xu, Zafaryab Haider +3
Modern machine learning (ML) pipelines depend heavily on third party libraries for graph compilation and hardware acceleration. While current practices audit data and model artifac…
HARP: Measuring Harm Amplification in Multi-Agent LLM Systems
Md Hafizur Rahman, Zafaryab Haider, Tanzim Mahfuz +1
Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability, but creates a propagation r…
DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
Abdullah Al Nomaan Nafi, Habibur Rahaman, Zafaryab Haider +4
Numerous techniques have been proposed for generating adversarial examples in white-box settings under strict Lp-norm constraints. However, such norm-bounded examples often fail to…
How a Bit Becomes a Story: Semantic Steering via Differentiable Fault Injection
Zafaryab Haider, Md Hafizur Rahman, Shane Moeykens +2
Hard-to-detect hardware bit flips, from either malicious circuitry or bugs, have already been shown to make transformers vulnerable in non-generative tasks. This work, for the firs…