9 papers
CISB-Bench: An Auditable Source--IR Dataset of Compiler-Introduced Security Bugs
Saatvik Pradhan, Anuroop Saini, Pranav Attrey +1
Compiler-introduced security bugs (CISBs) arise when an optimization, lowering, or instrumentation decision changes a security-relevant property of the generated program. They are…
Tool-Guided Retrieval-Augmented Repair for Securing LLM-Generated C Code
Vidyut Sriram, Saatvik Pradhan, Suman Saha
Large language models can generate C code from natural-language descriptions, but resulting programs often contain security vulnerabilities and compilation errors, posing risks for…
Evaluating LLM-Generated Obfuscated XSS Payloads for Machine Learning-Based Detection
Divyesh Gabbireddy, Suman Saha
Cross-site scripting (XSS) remains a persistent web security vulnerability, especially because obfuscation can change the surface form of a malicious payload while preserving its b…
SecureCodeRL: Security-Aware Reinforcement Learning for Code Generation with Partial-Credit Rewards
Suryansh Singh Sijwali, Suman Saha
Large Language Models (LLMs) can generate plausible code, but in settings that require exact stdin/stdout behavior they frequently produce programs that compile yet fail tests, and…
Improving LLM-Assisted Secure Code Generation through Retrieval-Augmented-Generation and Multi-Tool Feedback
Vidyut Sriram, Sawan Pandita, Achintya Lakshmanan +2
Large Language Models (LLMs) can generate code but often introduce security vulnerabilities, logical inconsistencies, and compilation errors. Prior work demonstrates that LLMs bene…
Rule-Based Approaches to Atomic Sentence Extraction
Lineesha Kamana, Akshita Ananda Subramanian, Mehuli Ghosh +1
Natural language often combines multiple ideas into complex sentences. Atomic sentence extraction, the task of decomposing complex sentences into simpler sentences that each expres…
Evolution of Buffer Management in Database Systems: From Classical Algorithms to Machine Learning and Disaggregated Memory
Prudhvi Gadupudi, Suman Saha
Buffer management remains a critical component of database and operating system performance, serving as the primary mechanism for bridging the persistent latency gap between CPU pr…
Can LLMs Recover Program Semantics? A Systematic Evaluation with Symbolic Execution
Rong Feng, Suman Saha
Obfuscation poses a persistent challenge for software engineering tasks such as program comprehension, maintenance, testing, and vulnerability detection. While compiler optimizatio…
Can Large Language Models Simulate Symbolic Execution Output Like KLEE?
Rong Feng, Vanisha Gupta, Vivek Patel +2
Symbolic execution helps check programs by exploring different paths based on symbolic inputs. Tools like KLEE are commonly used because they can automatically detect bugs and crea…