English
Related papers

Related papers: ShadowBound: Efficient Heap Memory Protection Thro…

200 papers

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…

Machine Learning · Computer Science 2024-06-03 Eleanor Clifford , Ilia Shumailov , Yiren Zhao , Ross Anderson , Robert Mullins

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…

Machine Learning · Computer Science 2025-06-03 Saad Hossain , Samanvay Vajpayee , Sirisha Rambhatla

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…

Cryptography and Security · Computer Science 2025-05-09 MD Mahady Hassan , Shanto Roy , Reza Rahaeimehr

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,…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-05-11 Inês Pinto Gouveia , Marcus Völp , Paulo Esteves-Verissimo

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…

Programming Languages · Computer Science 2023-05-08 Bastian Köpcke , Sergei Gorlatch , Michel Steuwer

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…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-10-24 Rana Ghazali , Douglas G. Down

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…

Artificial Intelligence · Computer Science 2025-07-16 Hari Masoor

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…

Cryptography and Security · Computer Science 2020-04-21 Pierpaolo Santucci , Emiliano Ingrassia , Giulio Picierro , Marco Cesati

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.…

Cryptography and Security · Computer Science 2019-09-20 Eyasu Getahun Chekole , Unnikrishnan Cheramangalath , Sudipta Chattopadhyay , Martin Ochoa , Guo Huaqun

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…

Cryptography and Security · Computer Science 2024-05-28 Jie Zhou , Mingshen Sun , John Criswell

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…

Cryptography and Security · Computer Science 2026-03-09 Mingkai Li , Joseph Devietti , Suman Jana , Tanvir Ahmed Khan

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…

Machine Learning · Computer Science 2022-11-02 Ganqu Cui , Lifan Yuan , Bingxiang He , Yangyi Chen , Zhiyuan Liu , Maosong Sun

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…

Software Engineering · Computer Science 2026-04-29 Huihui Huang , Jieke Shi , Bo Wang , Zhou Yang , David Lo

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…

Cryptography and Security · Computer Science 2025-10-24 Yu Hin Chan , Hao Yang , Shiyu Shen , Xingyu Fan , Shengzhe Lyu , Patrick S. Y. Hung , Ray C. C. Cheung

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…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-06-29 Ayoosh Bansal , Jayati Singh , Yifan Hao , Jen-Yang Wen , Renato Mancuso , Marco Caccamo

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…

Cryptography and Security · Computer Science 2025-09-10 Yitong Guo , Hongbo Chen , Haobin Hiroki Chen , Yukui Luo , XiaoFeng Wang , Chenghong Wang

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…

Cryptography and Security · Computer Science 2025-12-29 Xiaoya Lu , Dongrui Liu , Yi Yu , Luxin Xu , Jing Shao

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…

Cryptography and Security · Computer Science 2025-10-29 Tejaswini Bollikonda