Rahul Gupta

rahul1987iit's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 20 papers 1 day ago

FLIRT: Feedback Loop In-context Red Teaming

Paper • 2308.04265 • Published Aug 8, 2023 • 14

A Threshold Exceedance Framework for CBRN Uplift Evaluation in Frontier Language Models

Paper • 2607.12200 • Published 9 days ago • 3

Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition

Paper • 2604.17803 • Published Apr 20

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

Paper • 2606.02540 • Published Jun 1 • 10

From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs

Paper • 2511.14017 • Published Nov 18, 2025

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning

Paper • 2506.00876 • Published Jun 1, 2025

SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models

Paper • 2504.02883 • Published Apr 2, 2025

LUME: LLM Unlearning with Multitask Evaluations

Paper • 2502.15097 • Published Feb 27, 2025

Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework

Paper • 2604.22119 • Published Apr 23 • 6

Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs

Paper • 2603.21573 • Published Mar 23 • 1

When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents

Paper • 2602.08995 • Published Feb 9 • 2

Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning

Paper • 2504.01278 • Published Apr 2, 2025

Simulating and Understanding Deceptive Behaviors in Long-Horizon Interactions

Paper • 2510.03999 • Published Oct 5, 2025

D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models

Paper • 2509.17938 • Published Sep 22, 2025 • 4

Amazon Nova AI Challenge -- Trusted AI: Advancing secure, AI-assisted software development

Paper • 2508.10108 • Published Aug 13, 2025

Customize Multi-modal RAI Guardrails with Precedent-based predictions

Paper • 2507.20503 • Published Jul 28, 2025

Evaluating the Critical Risks of Amazon's Nova Premier under the Frontier Model Safety Framework

Paper • 2507.06260 • Published Jul 7, 2025 • 6

Establishing Best Practices for Building Rigorous Agentic Benchmarks

Paper • 2507.02825 • Published Jul 3, 2025 • 1

The Amazon Nova Family of Models: Technical Report and Model Card

Paper • 2506.12103 • Published Mar 17, 2025 • 1

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation

Paper • 2505.21784 • Published May 27, 2025 • 17