6 papers
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…
SoK: The Last Line of Defense: On Backdoor Defense Evaluation
Gorka Abad, Marina KrÄek, 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…
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…
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…
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…
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…