相关论文: Mon CH\'ERI: Mitigating Uninitialized Memory Acces…

Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute and memory intensive, where a single request can require…

In the main text published at USENIX Security 2025, we presented a systematic analysis of the role of cache occupancy in the design considerations for randomized caches (from the perspectives of performance and security). On the performance…

Approximate memory is a technique to mitigate the performance gap between memory subsystems and CPUs with its reduced access latency at a cost of data integrity. To gain benefit from approximate memory for realistic applications, it is…

As machine learning algorithms are shown to be an increasingly valuable tool, the demand for their access has grown accordingly. Oftentimes, it is infeasible to run inference with larger models without an accelerator, which may be…

Memory safety in complex applications implemented in unsafe programming languages such as C/C++ is still an unresolved problem in practice. Many different types of defenses have been proposed in the past to mitigate this problem. The most…

The emergence of resistive non-volatile memories opens the way to highly energy-efficient computation near- or in-memory. However, this type of computation is not compatible with conventional ECC, and has to deal with device unreliability.…

Large Language Models (LLMs) are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats, wherein LLMs offer cyber threat intelligence (CTI) to support vulnerability assessment and incident…

Memory corruption vulnerabilities are endemic to unsafe languages, such as C, and they can even be found in safe languages that themselves are implemented in unsafe languages or linked with libraries implemented in unsafe languages. Robust…

Low-level programming languages with weak/static type systems, such as C and C++, are vulnerable to errors relating to the misuse of memory at runtime, such as (sub-)object bounds overflows, (re)use-after-free, and type confusion. Such…

Current compilers implement security features and optimizations that require nontrivial semantic reasoning about pointers and memory allocation: the program after the insertion of the security feature, or after applying the optimization,…

Modern architectures require applications to make effective use of caches to achieve high performance and hide memory latency. This in turn requires careful consideration of placement of data in memory to exploit spatial locality, leverage…

Coarse-Grained Reconfigurable Arrays (CGRAs) are specialized accelerators commonly employed to boost performance in workloads with iterative structures. Existing research typically focuses on compiler or architecture optimizations aimed at…

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…

Dynamic Random Access Memory (DRAM) is pervasive in computer systems. Cell vulnerabilities caused by unintended phenomena (forced retention failure, latency alteration, rowhammer and rowpress) lead to unintended bit flips in memory. These…

Attackers willing to compromise computing systems can use malicious peripherals as an attack vector, threatening users that cannot verify the hardware's authenticity. To address this problem, our work uses the Security Protocol and Data…

The security of code generated by large language models (LLMs) is a significant concern, as studies indicate that such code often contains vulnerabilities and lacks essential defensive programming constructs. This work focuses on examining…

Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…

Trustworthy artificial intelligence increasingly relies on probabilistic computation to achieve robustness, interpretability, security and privacy. In practical systems, such workloads interleave deterministic data access with repeated…

Memory corruption is a serious class of software vulnerabilities, which requires careful attention to be detected and removed from applications before getting exploited and harming the system users. Symbolic execution is a well-known method…

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…