@article{oke2026absentia,title={{ABSENTIA}: Detecting Broken Access Control Vulnerabilities in Web Applications},author={Duarte, Andr{\'e} V. and Oke, Aditya and Melo, Rui and Gandhi, Shubham and Kotalwar, Nachiket and Khandor, Charmi and Wang, Danqing and Oliveira, Arlindo L. and Ros{\'e}, Carolyn and Li, Lei},journal={arXiv preprint},year={2026},month=oct,}
arXiv
Ulysses: A Security Harness For Synthesizing Verifiable Web Exploits
Aditya Oke, André Vicente Duarte, Rui Melo, and 6 more authors
@article{oke2026ulysses,title={{Ulysses}: A Security Harness For Synthesizing Verifiable Web Exploits},author={Oke, Aditya and Duarte, Andr{\'e} Vicente and Melo, Rui and Gandhi, Shubham and Kotalwar, Nachiket and Khandor, Charmi and Wang, Danqing and Ros{\'e}, Carolyn and Li, Lei},journal={arXiv preprint},year={2026},month=oct,}
arXiv
Self-Evolving Static Analysis via LLM Pseudo-Labeling
Rui Melo, André Duarte, Aditya Oke, and 5 more authors
@article{oke2026selfevolving,title={Self-Evolving Static Analysis via {LLM} Pseudo-Labeling},author={Melo, Rui and Duarte, Andr{\'e} and Oke, Aditya and Gandhi, Shubham and Kotalwar, Nachiket and Abreu, Rui and Li, Lei and Ros{\'e}, Carolyn},journal={arXiv preprint},year={2026},month=oct,}
How can we distinguish whether a peer review was written by a human or generated by an AI model? We argue that, in this setting, authorship should not be attributed solely from the textual features of a review, but also from the ideas, judgments, and claims it expresses. To this end, we propose Sem-Detect, an authorship detection method for peer reviews that operationalizes this principle by combining textual features with claim-level semantic analysis. Sem-Detect compares a target review against multiple AI-generated reviews of the same paper, leveraging the observation that different AI models tend to converge on similar points, while human reviewers introduce more unique and diverse ones. As a result, Sem-Detect is able to distinguish fully AI-generated reviews from authentic human-written ones, including those that have been refined using an LLM but still reflect human judgment. Across a dataset of over 20,000 peer reviews from ICLR and NeurIPS conferences, Sem-Detect improves over the strongest prior detector by 36.5% in TPR@1% FPR in the binary setting. More importantly, in the three-class scenario, we empirically show that LLM refinement preserves the semantic signals of human reviews, which remain distinct from the patterns exhibited by fully AI-generated text; as a result, fewer than 3.5% of LLM-refined human reviews are misclassified as AI-generated.
@inproceedings{duarte2026sem,title={Sem-Detect: Semantic Level Detection of {AI} Generated Peer-Reviews},author={Duarte, Andr{\'e} V. and Tufts, Brian and Oke, Aditya and Fang, Fei and Oliveira, Arlindo L. and Li, Lei},booktitle={The 43rd International Conference on Machine Learning (ICML)},location={Seoul, South Korea},year={2026},month=jul,}
This paper present an innovative approach for encryption and decryption using neural networks. Encryption and decryption are vital for the secure transmission of data as well as for maintaining security. The paper, presents a simple algorithm that uses Feed-Forward Networks to convert a given text into an encrypted message. Similarly, we use Feed-Forward networks to decrypt the message. Finally, the paper proposes an ensemble of networks to create a secure key based encryption algorithm.
@inproceedings{oke2022encryption,title={A Novel Approach to Encrypt Data Using Deep Neural Networks},author={Oke, Aditya and Kushwaha, Abhishek and Agrawal, Manan and Sahai, Utkrisht and Raman, Rahul},booktitle={The 2nd International Conference on Advances in Distributed Computing and Machine Learning},year={2022},publisher={Springer Singapore},address={Singapore},pages={467--475},isbn={978-981-16-4807-6},}