相关论文: ShadowBound: Efficient Heap Memory Protection Thro…
Early backdoor attacks against machine learning set off an arms race in attack and defence development. Defences have since appeared demonstrating some ability to detect backdoors in models or even remove them. These defences work by…
As large language models (LLMs) become ubiquitous, parameter-efficient fine-tuning methods and safety-first defenses have proliferated rapidly. However, the number of approaches and their recent increase have resulted in diverse…
Side-channel attacks on memory (SCAM) exploit unintended data leaks from memory subsystems to infer sensitive information, posing significant threats to system security. These attacks exploit vulnerabilities in memory access patterns, cache…
Today, leveraging the enormous modular power, diversity and flexibility of manycore systems-on-a-chip (SoCs) requires careful orchestration of complex resources, a task left to low-level software, e.g. hypervisors. In current architectures,…
Graphics Processing Units (GPU) offer tremendous computational power by following a throughput oriented computing paradigm where many thousand computational units operate in parallel. Programming this massively parallel hardware is…
Nowadays distributed computing environments, large amounts of data are generated from different resources with a high velocity, rendering the data difficult to capture, manage, and process within existing relational databases. Hadoop is a…
Current AI agent architectures suffer from ephemeral memory limitations, preventing effective collaboration and knowledge sharing across sessions and agent boundaries. We introduce SAMEP (Secure Agent Memory Exchange Protocol), a novel…
What is the best harness for cybersecurity AI? Cybersecurity systems are converging on a single execution scaffold per agent, an iterative shell loop driven by a Large Language Model (LLM). However, scaffolds are not interchangeable, rarely…
Cryptographic algorithm implementations are vulnerable to Cold Boot attacks, which consist in exploiting the persistence of RAM cells across reboots or power down cycles to read the memory contents and recover precious sensitive data. The…
Traditional memory management suffers from metadata overhead, architectural complexity, and stability degradation, problems intensified in cloud environments. Existing software/hardware optimizations are insufficient for cloud computing's…
Memory-safety attacks have been one of the most critical threats against computing systems. Although a wide-range of defense techniques have been developed against these attacks, the existing mitigation strategies have several limitations.…
Rust is one of the most promising systems programming languages to fundamentally solve the memory safety issues that have plagued low-level software for over forty years. However, to accommodate the scenarios where Rust's type rules might…
Modern computing is shifting from homogeneous CPU-centric systems to heterogeneous systems with closely integrated CPUs and GPUs. While the CPU software stack has benefited from decades of memory safety hardening, the GPU software stack…
Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…
Memory leaks remain prevalent in real-world C/C++ software. Static analyzers such as CodeQL provide scalable program analysis but frequently miss such bugs because they cannot recognize project-specific custom memory-management functions…
Privacy-preserving machine learning (PPML) is an emerging topic to handle secure machine learning inference over sensitive data in untrusted environments. Fully homomorphic encryption (FHE) enables computation directly on encrypted data on…
Real-time and cyber-physical systems need to interact with and respond to their physical environment in a predictable time. While multicore platforms provide incredible computational power and throughput, they also introduce new sources of…
While Trusted Execution Environments provide a strong foundation for secure cloud computing, they remain vulnerable to access pattern leakages. Oblivious Maps (OMAPs) mitigate this by fully hiding access patterns but suffer from high…
Despite the rapid development of safety alignment techniques for LLMs, defending against multi-turn jailbreaks is still a challenging task. In this paper, we conduct a comprehensive comparison, revealing that some existing defense methods…
As machine learning (ML) models become increasingly deployed through cloud infrastructures, the confidentiality of user data during inference poses a significant security challenge. Homomorphic Encryption (HE) has emerged as a compelling…