6 papers
Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs
Md Abdullah Al Mamun, Ngoc Phu Doan, Pedram Zaree +2
Large Language Models are increasingly trained on proprietary or sensitive data, from private healthcare and financial records to user conversations containing secrets. Ensuring th…
Batch Normalization Amplifies Memorization and Privacy Risks
Ngoc Phu Doan, Chongyan Gu, Ihsen Alouani
Batch Normalization (BN) is widely adopted to enable faster convergence and more stable training of deep neural networks. However, its impact on privacy and memorization has remain…
Bypassing Prompt Injection Detectors through Evasive Injections
Md Jahedur Rahman, Ihsen Alouani
Large language models (LLMs) are increasingly used in interactive and retrieval-augmented systems, but they remain vulnerable to prompt injection attacks, where injected secondary…
SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models
Omar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh +2
Safety alignment in Language Models (LMs) is fundamental for trustworthy AI. However, while different stakeholders are trying to leverage Arabic Language Models (ALMs), systematic…
AttenMIA: LLM Membership Inference Attack through Attention Signals
Pedram Zaree, Md Abdullah Al Mamun, Yue Dong +2
Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency…
Emerging Threats and Countermeasures in Neuromorphic Systems: A Survey
Pablo Sorrentino, Stjepan Picek, Ihsen Alouani +5
Neuromorphic computing mimics brain-inspired mechanisms through spiking neurons and energy-efficient processing, offering a pathway to efficient in-memory computing (IMC). However,…