6 papers
NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning
Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung +2
Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge transfer, which can impede their…
DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Escalation
Shaghayegh Sadeghi, Khashayar Khajavi, Rise Adhikari +1
Misalignment between claims and their cited evidence is a common failure mode in reports generated by large language models, limiting their reliability in scientific and other high…
CiteCheck: Retrieval-Grounded Detection of LLM Citation Hallucinations in Scientific Text
Khashayar Khajavi, Shaghayegh Sadeghi, Rise Adhikari +1
Large language models (LLMs) are increasingly used to generate scientific reports, but they can produce references that appear plausible while containing corrupted metadata or poin…
Lightening the Load: A Cluster-Based Framework for A Lower-Overhead, Provable Website Fingerprinting Defense
Khashayar Khajavi, Tao Wang
Website fingerprinting (WF) attacks remain a significant threat to encrypted traffic, prompting the development of a wide range of defenses. Among these, two prominent classes are…
Reality Check for Tor Website Fingerprinting in the Open World
Mohammadhamed Shadbeh, Khashayar Khajavi, Tao Wang
Website fingerprinting (WF) attacks on Tor can infer user destinations from encrypted traffic metadata. However, their real-world effectiveness remains debated due to laboratory se…
Preserving Plasticity in Continual Learning with Adaptive Linearity Injection
Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung +2
Loss of plasticity in deep neural networks is the gradual reduction in a model's capacity to incrementally learn and has been identified as a key obstacle to learning in non-statio…