8 citations · 8 across the 7 of their papers we have counts for
8 papers
SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents
Saswat Das, Parvati Viswanathan, Daniel Donnelly +3
Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their controller instructions, memory management…
Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
Mason Nakamura, Abhinav Kumar, Saswat Das +5
Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety…
NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents
Saswat Das, Ferdinando Fioretto
Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities enable transformative applications in domains spanni…
Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents
Saswat Das, Jameson Sandler, Ferdinando Fioretto
LLM agents have begun to appear as personal assistants, customer service bots, and clinical aides. While these applications deliver substantial operational benefits, they also requ…
Fairness Issues and Mitigations in (Differentially Private) Socio-Demographic Data Processes
Joonhyuk Ko, Juba Ziani, Saswat Das +2
Statistical agencies rely on sampling techniques to collect socio-demographic data crucial for policy-making and resource allocation. This paper shows that surveys of important soc…
Low-rank finetuning for LLMs: A fairness perspective
Saswat Das, Marco Romanelli, Cuong Tran +3
Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models (LLMs) due to their reduced computational and memory requirements. This pa…
Advances in Differential Privacy and Differentially Private Machine Learning
Saswat Das, Subhankar Mishra
There has been an explosion of research on differential privacy (DP) and its various applications in recent years, ranging from novel variants and accounting techniques in differen…
Disparate Impact on Group Accuracy of Linearization for Private Inference
Saswat Das, Marco Romanelli, Ferdinando Fioretto
Ensuring privacy-preserving inference on cryptographically secure data is a well-known computational challenge. To alleviate the bottleneck of costly cryptographic computations in…