~ similar to 2606.18400· 20 results
Cloak is an oblivious storage system that significantly improves the performance of ORAM by exploiting temporal locality, achieving low overheads while maintaining security.
The paper analyzes the bit-flip vulnerability of shared KV-cache blocks in LLM serving systems, demonstrating that these blocks are susceptible to silent, persistent, and selective data corruption.
The paper characterizes 'dead-entry' TLB misses in GPUs, which occur when recently evicted translations are immediately re-walked, and proposes DEPOT, a Bloom filter mechanism that significantly reduc…
The paper introduces CIPL, a unified channel-oriented framework, demonstrating that privacy leakage in LLM agents is governed by observable data channels and pipeline interactions, rather than being l…
Venish Patidar, Dhruv Bindra, Ahmed Darwich, Josh Brown +2 more
This paper proposes a decentralized, confidential computing platform using Intel TDX, ITA, and NVIDIA CC for secure and affordable AI workloads.
This paper presents a novel data-free Membership Inference Attack (MIA) that uses gradient inversion on Standard Cell Library Layouts (SCLLs) to reconstruct sensitive hardware images from intercepted…
Tessera introduces a novel hardware architecture that achieves secure, near-line-rate weight streaming for DNNs on UMA edge accelerators by performing cache-line granularity decryption during DRAM fet…
This paper proposes a novel decompiler-based approach called VMSpec to automate the construction of VM processor specifications, enabling existing decompilers to analyze VM-obfuscated code.
This paper proposes DataGuard, a hardware-based mechanism to ensure differential privacy in federated learning without trusting a third-party application.
The paper proposes a method for bit-exact verification of AI inference outputs without sacrificing performance, demonstrating that deterministic, precise re-computation is possible even across differe…
EncFormer is a novel two-party framework that significantly improves the efficiency and scalability of private Transformer inference by optimizing the combination of Fully Homomorphic Encryption (FHE)…
The paper introduces VMPredator, an automated tool that analyzes and deobfuscates virtualization obfuscation in malware by extracting semantic units, successfully restoring program functionality with…
Yunze Zhao, Yibo Zhao, Yuchen Zhang, Zaoxing Liu +1 more
The paper introduces GRIEF, a greybox fuzzer that discovers critical, concurrency-related vulnerabilities in LLM serving systems by treating timed multi-request traces as inputs, finding issues like c…
Sangjun An, Hyeyeon Park, Yejin Son, Seoksu Lee +1 more
The paper proposes a novel framework to analyze large, obfuscated binaries by decomposing them into structurally coherent units, enabling large-scale dataset generation for LLM-based analysis.
The paper proposes PrISM, an intersection-based probabilistic mitigation technique that significantly improves the scalability of RowHammer defense at low thresholds by correlating sampled row history…
This paper investigates the persistence of a timing side channel through the shared page cache in modern cloud platforms with various isolation mechanisms.
Chris S. Lin, Yuqin Yan, Guozhen Ding, Joyce Qu +3 more
This paper demonstrates a novel GPU-side privilege escalation attack, showing that Rowhammer can be used to target and tamper with page tables to gain unauthorized access to co-tenant memory and ultim…
The paper systematically evaluates various defense mechanisms against persistent memory attacks on LLM agents, finding that only tool-gating at the memory layer (Memory Sandbox) effectively mitigates…
This paper introduces a dual-layer side-channel attack framework that exploits the variable workload introduced by dynamic image preprocessing in local Vision-Language Models (VLMs) to infer sensitive…