Shuvalaxmi Dass

Mohammad Farhad, Shuvalaxmi Dass

Software security relies on effective vulnerability detection and patching, yet determining whether a patch fully eliminates risk remains an underexplored challenge. Existing vulnerability benchmarks often treat patched functions as inherently benign, overlooking the possibility of residual security risks. In this work, we analyze vulnerable-benign function pairs from the PrimeVul, a benchmark dataset using multiple code language models (Code LMs) to capture semantic similarity, complemented by Tree-sitter-based abstract syntax tree (AST) analysis for structural similarity. Building on these signals, we propose Residual Risk Scoring (RRS), a unified framework that integrates embedding-based semantic similarity, localized AST-based structural similarity, and cross-model agreement to estimate residual risk in code. Our analysis shows that benign functions often remain highly similar to their vulnerable counterparts both semantically and structurally, indicating potential persistence of residual risk. We further find that approximately $61\%$ of high-RRS code pairs exhibit $13$ distinct categories of residual issues (e.g., null pointer dereferences, unsafe memory allocation), validated using state-of-the-art static analysis tools including Cppcheck, Clang-Tidy, and Facebook-Infer. These results demonstrate that code-level similarity provides a practical signal for prioritizing post-patch inspection, enabling more reliable and scalable security assessment in real-world open-source software pipelines.

Mohammad Farhad, Sabbir Rahman, Shuvalaxmi Dass

Software security testing, particularly when enhanced with deep learning models, has become a powerful approach for improving software quality, enabling faster detection of known flaws in source code. However, many approaches miss post-fix latent vulnerabilities that remain even after patches typically due to incomplete fixes or overlooked issues may later lead to zero-day exploits. In this paper, we propose $HYDRA$, a $Hy$brid heuristic-guided $D$eep $R$epresentation $A$rchitecture for predicting latent zero-day vulnerabilities in patched functions that combines rule-based heuristics with deep representation learning to detect latent risky code patterns that may persist after patches. It integrates static vulnerability rules, GraphCodeBERT embeddings, and a Variational Autoencoder (VAE) to uncover anomalies often missed by symbolic or neural models alone. We evaluate HYDRA in an unsupervised setting on patched functions from three diverse real-world software projects: Chrome, Android, and ImageMagick. Our results show HYDRA predicts 13.7%, 20.6%, and 24% of functions from Chrome, Android, and ImageMagick respectively as containing latent risks, including both heuristic matches and cases without heuristic matches ($None$) that may lead to zero-day vulnerabilities. It outperforms baseline models that rely solely on regex-derived features or their combination with embeddings, uncovering truly risky code variants that largely align with known heuristic patterns. These results demonstrate HYDRA's capability to surface hidden, previously undetected risks, advancing software security validation and supporting proactive zero-day vulnerabilities discovery.

Mohoshin Ara Tahera, Karamveer Singh Sidhu, Shuvalaxmi Dass et al.

Large Language Models (LLMs) are increasingly adopted in healthcare to support clinical decision-making, summarize electronic health records (EHRs), and enhance patient care. However, this integration introduces significant privacy and security challenges, driven by the sensitivity of clinical data and the high-stakes nature of medical workflows. These risks become even more pronounced across heterogeneous deployment environments, ranging from small on-premise hospital systems to regional health networks, each with unique resource limitations and regulatory demands. This Systematization of Knowledge (SoK) examines the evolving threat landscape across the three core LLM phases: Data preprocessing, Fine-tuning, and Inference within realistic healthcare settings. We present a detailed threat model that characterizes adversaries, capabilities, and attack surfaces at each phase, and we systematize how existing privacy-preserving techniques (PPTs) attempt to mitigate these vulnerabilities. While existing defenses show promise, our analysis identifies persistent limitations in securing sensitive clinical data across diverse operational tiers. We conclude with phase-aware recommendations and future research directions aimed at strengthening privacy guarantees for LLMs in regulated environments. This work provides a foundation for understanding the intersection of LLMs, threats, and privacy in healthcare, offering a roadmap toward more robust and clinically trustworthy AI systems.

Mohoshin Ara Tahera, Sabbir Rahman, Shuvalaxmi Dass et al.

Federated real-time object detection using transformers in Intelligent Transportation Systems (ITS) faces three major challenges: (1) missing-class non-IID data heterogeneity from geographically diverse traffic environments, (2) latency constraints on edge hardware for high-capacity transformer models, and (3) privacy and security risks from untrusted client updates and centralized aggregation. We propose BlockSecRT-DETR, a BLOCKchain-SECured Real-Time Object DEtection TRansformer framework for ITS that provides a decentralized, token-efficient, and privacy-preserving federated training solution using RT-DETR transformer, incorporating a blockchain-secured update validation mechanism for trustworthy aggregation. In this framework, challenges (1) and (2) are jointly addressed through a unified client-side design that integrates RT-DETR training with a Token Engineering Module (TEM). TEM prunes low-utility tokens, reducing encoder complexity and latency on edge hardware, while aggregated updates mitigate non-IID data heterogeneity across clients. To address challenge (3), BlockSecRT-DETR incorporates a decentralized blockchain-secured update validation mechanism that enables tamper-proof, privacy-preserving, and trust-free authenticated model aggregation without relying on a central server. We evaluated the proposed framework under a missing-class Non-IID partition of the KITTI dataset and conducted a blockchain case study to quantify security overhead. TEM improves inference latency by 17.2% and reduces encoder FLOPs by 47.8%, while maintaining global detection accuracy (89.20% mAP@0.5). The blockchain integration adds 400 ms per round, and the ledger size remains under 12 KB due to metadata-only on-chain storage.

Shuvalaxmi Dass, Prerit Datta, Akbar Siami Namin

It is important to predict any adversarial attacks and their types to enable effective defense systems. Often it is hard to label such activities as malicious ones without adequate analytical reasoning. We propose the use of Hidden Markov Model (HMM) to predict the family of related attacks. Our proposed model is based on the observations often agglomerated in the form of log files and from the target or the victim's perspective. We have built an HMM-based prediction model and implemented our proposed approach using Viterbi algorithm, which generates a sequence of states corresponding to stages of a particular attack. As a proof of concept and also to demonstrate the performance of the model, we have conducted a case study on predicting a family of attacks called Action Spoofing.

Shuvalaxmi Dass, Akbar Siami Namin

Mainstream software applications and tools are the configurable platforms with an enormous number of parameters along with their values. Certain settings and possible interactions between these parameters may harden (or soften) the security and robustness of these applications against some known vulnerabilities. However, the large number of vulnerabilities reported and associated with these tools make the exhaustive testing of these tools infeasible against these vulnerabilities infeasible. As an instance of general software testing problem, the research question to address is whether the system under test is robust and secure against these vulnerabilities. This paper introduces the idea of ``vulnerability coverage,'' a concept to adequately test a given application for a certain classes of vulnerabilities, as reported by the National Vulnerability Database (NVD). The deriving idea is to utilize the Common Vulnerability Scoring System (CVSS) as a means to measure the fitness of test inputs generated by evolutionary algorithms and then through pattern matching identify vulnerabilities that match the generated vulnerability vectors and then test the system under test for those identified vulnerabilities. We report the performance of two evolutionary algorithms (i.e., Genetic Algorithms and Particle Swarm Optimization) in generating the vulnerability pattern vectors.

Shuvalaxmi Dass, Xiaozhen Xue, Akbar Siami Namin

The performance of coverage-based fault localization greatly depends on the quality of test cases being executed. These test cases execute some lines of the given program and determine whether the underlying tests are passed or failed. In particular, some test cases may be well-behaved (i.e., passed) while executing faulty statements. These test cases, also known as coincidentally correct test cases, may negatively influence the performance of the spectra-based fault localization and thus be less helpful as a tool for the purpose of automated debugging. In other words, the involvement of these coincidentally correct test cases may introduce noises to the fault localization computation and thus cause in divergence of effectively localizing the location of possible bugs in the given code. In this paper, we propose a hybrid approach of ensemble learning combined with a supervised learning algorithm namely, Random Forests (RF) for the purpose of correctly identifying test cases that are mislabeled to be the passing test cases. A cost-effective analysis of flipping the test status or trimming (i.e., eliminating from the computation) the coincidental correct test cases is also reported.

Shuvalaxmi Dass, Akbar Siami Namin

We present a novel idea on adequacy testing called ``{vulnerability coverage}.'' The introduced coverage measure examines the underlying software for the presence of certain classes of vulnerabilities often found in the National Vulnerability Database (NVD) website. The thoroughness of the test input generation procedure is performed through the adaptation of evolutionary algorithms namely Genetic Algorithms (GA) and Particle Swarm Optimization (PSO). The methodology utilizes the Common Vulnerability Scoring System (CVSS), a free and open industry standard for assessing the severity of computer system security vulnerabilities, as a fitness measure for test inputs generation. The outcomes of these evolutionary algorithms are then evaluated in order to identify the vulnerabilities that match a class of vulnerability patterns for testing purposes.