Related papers: No Attack Required: Semantic Fuzzing for Specifica…
Testing-based methodologies like fuzzing are able to analyze complex software which is not amenable to traditional formal approaches like verification, model checking, and abstract interpretation. Despite enormous success at exposing…
Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection…
Modern generator-based fuzzing techniques combine lightweight input generators with coverage-guided mutation as a method of exploring deep execution paths in a target program. A complimentary approach in prior research focuses on creating…
Fuzzing continues to be the most effective method for identifying security vulnerabilities in software. In the context of fuzz testing, the fuzzer supplies varied inputs to fuzz targets, which are designed to comprehensively exercise…
Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…
Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…
Modern computing systems heavily rely on hardware as the root of trust. However, their increasing complexity has given rise to security-critical vulnerabilities that cross-layer at-tacks can exploit. Traditional hardware vulnerability…
The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…
Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been…
Expressing class specifications via executable constraints is important for various software engineering tasks such as test generation, bug finding and automated debugging, but developers rarely write them. Techniques that infer…
Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…
We present a novel tool BertRLFuzzer, a BERT and Reinforcement Learning (RL) based fuzzer aimed at finding security vulnerabilities for Web applications. BertRLFuzzer works as follows: given a set of seed inputs, the fuzzer performs…
Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…
Software fuzzing has become a cornerstone in automated vulnerability discovery, yet existing mutation strategies often lack semantic awareness, leading to redundant test cases and slow exploration of deep program states. In this work, I…
Implementations of network protocols are often prone to vulnerabilities caused by developers' mistakes when accessing memory regions and dealing with arithmetic operations. Finding practical approaches for checking the security of network…
Fuzz testing of software libraries relies on fuzz drivers to invoke library APIs. Traditionally, these drivers are written manually by developers - a process that is time-consuming and often inadequate for exercising complex program…
LLM-based SOC log classifiers are commonly evaluated using regular-expression pipelines that extract structured fields from free-form model output. We demonstrate that this practice introduces a class of silent, systematic evaluation…
Fuzzing has gained in popularity for software vulnerability detection by virtue of the tremendous effort to develop a diverse set of fuzzers. Thanks to various fuzzing techniques, most of the fuzzers have been able to demonstrate great…
Command-line interface (CLI) fuzzing tests programs by mutating both command-line options and input file contents, thus enabling discovery of vulnerabilities that only manifest under specific option-input combinations. Prior works of CLI…
The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…