密码学与安全
Concerns about big tech's monopoly power have featured prominently in recent media and policy discourse, as regulators across the European Union (EU), the United States (US) and beyond have ramped up efforts to promote healthier market…
Machine learning (ML) has gained significant adoption in Android malware detection to address the escalating threats posed by the rapid proliferation of malware attacks. However, recent studies have revealed the inherent vulnerabilities of…
Boolean satisfiability (SAT) solvers are widely used in hardware verification, cryptanalysis, automatic test-pattern generation, and side-channel reasoning workflows. Modern conflict-driven clause-learning (CDCL) solvers are highly…
Memory-safety violations in C and C++ programs continue to enable sophisticated exploitation techniques such as control-flow hijacking and data-oriented attacks. Existing hardware defenses either rely on address space layout randomization…
Developers create modern software applications (Apps) on top of third-party libraries (Libs). When library vulnerabilities are reachable through application code, the applications can be vulnerable to software supply chain attacks. Prior…
Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing safety alignment evaluates overt requests in isolation,…
The recent surge in security concerns for IoT devices highlights the increasing threat of cryptographic vulnerabilities. These weaknesses can lead to unauthorized access, data breaches, and manipulation of device functions, compromising the…
NVIDIA GPUs with GDDR memories have been shown susceptible to Rowhammer-based bit-flips, similar to CPUs. However, Rowhammer exploits on GPUs have been limited to injecting untargeted bit-flips in victim data like weights of machine…
The exponential growth of the Internet of Things (IoT) has integrated connected devices into various sectors like smart cities, digital health, and Industry 4.0, generating vast amounts of real-time data to support intelligent…
Smart contracts on blockchains are prone to diverse security vulnerabilities that can lead to significant financial losses due to their immutable nature. Existing detection approaches often lack flexibility across vulnerability types and…
Data valuation is a foundational task in data marketplaces, where a Shapley-value attribution determines how a buyer's payment is distributed among data providers. Typically, the marketplace operator runs this attribution alone, requiring…
Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…
Acoustic side-channel attacks (ASCA) on keyboards pose a significant security risk, as keystrokes can be inferred from typing acoustics, revealing sensitive information. Prior ASCA studies are limited by small-scale datasets with restricted…
The rise of Large Language Model (LLM) agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among them, prompt injection attacks, where adversaries embed malicious instructions into the agent…
As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user-agent-environment interactions to pursue malicious objectives…
LLM agents release private data across multi-service interactions. Existing prompt sanitizers based on metric differential privacy treat each release independently, so adversaries combining releases across turns can recover private…
Existing benchmarks of language-model refusal on malicious-coding tasks routinely conflate requests for executable malicious software with requests for harmful security knowledge. This conflation matters because the two request types…
We introduce HackerSignal, a benchmark for temporal out-of-distribution cyber threat intelligence (CTI) and cross-source CVE linkage. HackerSignal aggregates 7.45 million exact-deduplicated documents from 64 public forum/source identifiers…
Large Language Models (LLMs) are increasingly being used as security engineering tools to summarize and explain malware behavior to analysts. A common assumption is that Retrieval-Augmented Generation (RAG) improves explanation quality by…
Zero-day attacks pose severe cybersecurity risks due to their high success rates and stealth. Because signature-based approaches struggle to detect such attacks, building Intrusion Detection Systems (IDSs) for detecting zero-day attacks is…