collaborators

6 papers

cs.CR2025

Towards Backdoor Stealthiness in Model Parameter Space

Xiaoyun Xu, Zhuoran Liu, Stefanos Koffas +1

Recent research on backdoor stealthiness focuses mainly on indistinguishable triggers in input space and inseparable backdoor representations in feature space, aiming to circumvent…

cs.CR2025

SoK: The Last Line of Defense: On Backdoor Defense Evaluation

Gorka Abad, Marina Krček, Stefanos Koffas +7

Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been…

cs.SE2025

Interpreting Performance Profiles with Deep Learning

Zhuoran Liu

Profiling tools (also known as profilers) play an important role in understanding program performance at runtime, such as hotspots, bottlenecks, and inefficiencies. While profilers…

cs.ET2025

Towards Efficient Key-Value Cache Management for Prefix Prefilling in LLM Inference

Yue Zhu, Hao Yu, Chen Wang +2

The increasing adoption of large language models (LLMs) with extended context windows necessitates efficient Key-Value Cache (KVC) management to optimize inference performance. Inf…

cs.LG2025

Solving Situation Puzzles with Large Language Model and External Reformulation

Kun Li, Xinwei Chen, Tianyou Song +5

In recent years, large language models (LLMs) have shown an impressive ability to perform arithmetic and symbolic reasoning tasks. However, we found that LLMs (e.g., ChatGPT) canno…

cs.LG2024

BAN: Detecting Backdoors Activated by Adversarial Neuron Noise

Xiaoyun Xu, Zhuoran Liu, Stefanos Koffas +2

Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversio…