Achintya Desai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Achintya Desai has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Tevfik Bultan
Computer Science, University of California, Santa Barbara, Santa Barbara, California, USA
4 shared publications - Md Shafiuzzaman
University of California at Santa Barbara, Goleta, USA
3 shared publications - Laboni Sarker
Computer Science, University of California Santa Barbara, Santa Barbara, California, USA
2 shared publications - Anoop Namboodiri
IIIT-Hyderabad
1 shared publication - Kannan Srinathan
International Institute of Information Technology
1 shared publication - Mahima Chaudhary
University of California at Santa Barbara, Goleta, USA
1 shared publication
Latest Publications
- Open Access
- 8 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 66-76
Bug Composition: Triggering Multiple Bugs with Agentic Driver Generation
- 8 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 66-76
Open AccessBug Composition: Triggering Multiple Bugs with Agentic Driver Generation
- Open Access
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 2475-2497
PAGENT: Program Analysis Guided LLM Agent for Proof-of-Concept Generation
Software developers frequently receive vulnerability reports that require them to reproduce the vulnerability in a reliable manner by generating a proof-of-concept (PoC) input that triggers it. Given the source code for a software project and a specific code location for a potential vulnerability, automatically generating a PoC for the given vulnerability has been a challenging research problem. Symbolic execution and fuzzing techniques require expert guidance and manual steps and face scalability challenges for PoC generation. Although recent advances in LLMs have increased the level of automation and scalability, the success rate of PoC generation with LLMs remains quite low. In this paper, we present a novel approach called Program Analysis Guided proof of concept generation agENT (PAGENT) that is scalable and significantly improves the success rate of LLM-based automated PoC generation compared to prior results. PAGENT integrates lightweight and rule-based static analysis phases for providing static analysis guidance and sanitizer-based profiling and coverage information for providing dynamic analysis guidance with a PoC generation agent. Our experiments demonstrate that the resulting hybrid approach significantly outperforms the prior top-performing agentic approach by 132% for the PoC generation task across 10 open-source projects. PAGENT also discovered 32 post-patch PoCs that trigger the vulnerability in the patched version of the source code, with 2 reproducing the crash in the most recent versions.
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 2475-2497
Open AccessPAGENT: Program Analysis Guided LLM Agent for Proof-of-Concept Generation
Software developers frequently receive vulnerability reports that require them to reproduce the vulnerability in a reliable manner by generating a proof-of-concept (PoC) input that triggers it. Given the source code for a software project and a specific code location for a potential vulnerability, automatically generating a PoC for the given vulnerability has been a challenging research problem. Symbolic execution and fuzzing techniques require expert guidance and manual steps and face scalability challenges for PoC generation. Although recent advances in LLMs have increased the level of automation and scalability, the success rate of PoC generation with LLMs remains quite low. In this paper, we present a novel approach called Program Analysis Guided proof of concept generation agENT (PAGENT) that is scalable and significantly improves the success rate of LLM-based automated PoC generation compared to prior results. PAGENT integrates lightweight and rule-based static analysis phases for providing static analysis guidance and sanitizer-based profiling and coverage information for providing dynamic analysis guidance with a PoC generation agent. Our experiments demonstrate that the resulting hybrid approach significantly outperforms the prior top-performing agentic approach by 132% for the PoC generation task across 10 open-source projects. PAGENT also discovered 32 post-patch PoCs that trigger the vulnerability in the patched version of the source code, with 2 reproducing the crash in the most recent versions.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 17-28
Assessing, Exploiting, and Mitigating Syntactic Robustness Failures in LLM-Based Code Generation
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 17-28
Open AccessAssessing, Exploiting, and Mitigating Syntactic Robustness Failures in LLM-Based Code Generation
- Open Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1783-1794
STASE: Static Analysis Guided Symbolic Execution for UEFI Vulnerability Signature Generation
Since its major release in 2006, the Unified Extensible Firmware Interface (UEFI) has become the industry standard for interfacing a computer's hardware and operating system, replacing BIOS. UEFI has higher privileged security access to system resources than any other software component, including the system kernel. Hence, identifying and characterizing vulnerabilities in UEFI is extremely important for computer security. However, automated detection and characterization of UEFI vulnerabilities is a challenging problem. Static vulnerability analysis techniques are scalable but lack precision (reporting many false positives), whereas symbolic analysis techniques are precise but are hampered by scalability issues due to path explosion and the cost of constraint solving. In this paper, we introduce a technique called STatic Analysis guided Symbolic Execution (STASE), which integrates both analysis approaches to leverage their strengths and minimize their weaknesses. We begin with a rule-based static vulnerability analysis on LLVM bitcode to identify potential vulnerability targets for symbolic execution. We then focus symbolic execution on each target to achieve precise vulnerability detection and signature generation. STASE relies on the manual specification of reusable vulnerability rules and attacker-controlled inputs. However, it automates the generation of harnesses that guide the symbolic execution process, addressing the usability and scalability of symbolic execution, which typically requires manual harness generation to reduce the state space. We implemented and applied STASE to the implementations of UEFI code base. STASE detects and generates vulnerability signatures for 5 out of 9 recently reported PixieFail vulnerabilities and 13 new vulnerabilities in Tianocore's EDKII codebase.
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1783-1794
Open AccessSTASE: Static Analysis Guided Symbolic Execution for UEFI Vulnerability Signature Generation
Since its major release in 2006, the Unified Extensible Firmware Interface (UEFI) has become the industry standard for interfacing a computer's hardware and operating system, replacing BIOS. UEFI has higher privileged security access to system resources than any other software component, including the system kernel. Hence, identifying and characterizing vulnerabilities in UEFI is extremely important for computer security. However, automated detection and characterization of UEFI vulnerabilities is a challenging problem. Static vulnerability analysis techniques are scalable but lack precision (reporting many false positives), whereas symbolic analysis techniques are precise but are hampered by scalability issues due to path explosion and the cost of constraint solving. In this paper, we introduce a technique called STatic Analysis guided Symbolic Execution (STASE), which integrates both analysis approaches to leverage their strengths and minimize their weaknesses. We begin with a rule-based static vulnerability analysis on LLVM bitcode to identify potential vulnerability targets for symbolic execution. We then focus symbolic execution on each target to achieve precise vulnerability detection and signature generation. STASE relies on the manual specification of reusable vulnerability rules and attacker-controlled inputs. However, it automates the generation of harnesses that guide the symbolic execution process, addressing the usability and scalability of symbolic execution, which typically requires manual harness generation to reduce the state space. We implemented and applied STASE to the implementations of UEFI code base. STASE detects and generates vulnerability signatures for 5 out of 9 recently reported PixieFail vulnerabilities and 13 new vulnerabilities in Tianocore's EDKII codebase.
- Open Access
- 15 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
S-BAN: Secure Biometric Authentication using Noise
Biometric signal consisting of irrelevant or non-distinctive features can contain useful correlational properties that privacy-preserving verification schemes can exploit. While an efficient protocol for iris verification using noise has been presented [33], it is not applicable to other widely used modalities, i.e., face and fingerprint, since the methods of noise extraction and comparison are different. In this work, we design a verification protocol for secure dot product computation and also propose noise extraction mechanisms for face and fingerprint modalities. We evaluate the performance of the protocol on CFP, LFW, CelebA, FVC 2004 DB1A, DB2A, DB3A, and SOCOFing datasets. While the protocol exhibits a slight degradation in accuracy, it provides information-theoretic security with a practical computational complexity.
- 15 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessS-BAN: Secure Biometric Authentication using Noise
Biometric signal consisting of irrelevant or non-distinctive features can contain useful correlational properties that privacy-preserving verification schemes can exploit. While an efficient protocol for iris verification using noise has been presented [33], it is not applicable to other widely used modalities, i.e., face and fingerprint, since the methods of noise extraction and comparison are different. In this work, we design a verification protocol for secure dot product computation and also propose noise extraction mechanisms for face and fingerprint modalities. We evaluate the performance of the protocol on CFP, LFW, CelebA, FVC 2004 DB1A, DB2A, DB3A, and SOCOFing datasets. While the protocol exhibits a slight degradation in accuracy, it provides information-theoretic security with a practical computational complexity.