1 citations · 1 across the 11 of their papers we have counts for
11 papers
Hoss: Fast Oblivious Semantic Search with Heterogeneous GPU-CPU-TEE Architecture
Jianzhang Du, Weijie Huang, Chenghong Wang +4
Semantic search is widely deployed in modern AI systems, but protecting both data contents and access patterns remains challenging. The current state-of-the-art system, Compass, ac…
SMTrap: Cost-Effective DoS Attacks Against Large Reasoning Models via SMT Conflict Guidance
Jian Yang, Zhenqi Feng, Zhaoyang Yu +7
Existing LRM-DoS methods rely heavily on model feedback to synthesize attack queries, requiring either repeated queries to the target model or training a dedicated attack model. Th…
Bulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities
Qiyuan Fan, Zhi Li, Junjie Li +3
Container filesystem isolation depends on safely resolving container-controlled paths during privileged host-container interactions. As third-party plugins and agent sandboxes intr…
Autonomous LLM Agent Worms: Cross-Platform Propagation, Automated Discovery and Temporal Re-Entry Defense
Mingming Zha, Xiaofeng Wang
Autonomous LLM agents operate as long-running processes with persistent workspaces, memory files, scheduled task state, and messaging integrations. These features create a new prop…
BOLT: Bandwidth-Optimized Lightning-Fast Oblivious Map powered by Secure HBM Accelerators
Yitong Guo, Hongbo Chen, Haobin Hiroki Chen +3
While Trusted Execution Environments provide a strong foundation for secure cloud computing, they remain vulnerable to access pattern leakages. Oblivious Maps (OMAPs) mitigate this…
Characterizing Trust Boundary Vulnerabilities in TEE Containers: An Empirical Study
Weijie Liu, Hongbo Chen, Shuo Huai +7
Trusted Execution Environments (TEEs) have become a cornerstone of confidential computing, attracting significant attention from academia and industry. To support secure and scalab…
Picachv: Formally Verified Data Use Policy Enforcement for Secure Data Analytics
Haobin Hiroki Chen, Hongbo Chen, Mingshen Sun +2
Ensuring the proper use of sensitive data in analytics under complex privacy policies is an increasingly critical challenge. Many existing approaches lack portability, verifiabilit…
Disassembling Obfuscated Executables with LLM
Huanyao Rong, Yue Duan, Hang Zhang +4
Disassembly is a challenging task, particularly for obfuscated executables containing junk bytes, which is designed to induce disassembly errors. Existing solutions rely on heurist…
Agora: Trust Less and Open More in Verification for Confidential Computing
Hongbo Chen, Quan Zhou, Sen Yang +4
Binary verification plays a pivotal role in software security, yet building a verification service that is both open and trustworthy poses a formidable challenge. In this paper, we…
LineBreaker: Finding Token-Inconsistency Bugs with Large Language Models
Hongbo Chen, Yifan Zhang, Xing Han +7
Token-inconsistency bugs (TIBs) involve the misuse of syntactically valid yet incorrect code tokens, such as misused variables and erroneous function invocations, which can often l…
Toward Unbiased Multiple-Target Fuzzing with Path Diversity
Huanyao Rong, Wei You, Xiaofeng Wang +1
In this paper, we propose a novel directed fuzzing solution named AFLRun, which features target path-diversity metric and unbiased energy assignment. Firstly, we develop a new cove…