Copertina

DoomArena: A framework for Testing AI Agents Against Evolving Security Threats

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Boisvert, Leo, Bansal, Mihir, Evuru, Chandra Kiran Reddy, Huang, Gabriel, Puri, Abhay, Bose, Avinandan, Fazel, Maryam, Cappart, Quentin, Stanley, Jason, Lacoste, Alexandre, Drouin, Alexandre, Dvijotham, Krishnamurthy
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
di: Boisvert, Léo, et al.
Pubblicazione: (2025)

Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning
di: Bose, Avinandan, et al.
Pubblicazione: (2025)

WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
di: Boisvert, Léo, et al.
Pubblicazione: (2024)

WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
di: Drouin, Alexandre, et al.
Pubblicazione: (2024)

Towards a Generic Representation of Combinatorial Problems for Learning-Based Approaches
di: Boisvert, Léo, et al.
Pubblicazione: (2024)

Offline Multi-task Transfer RL with Representational Penalization
di: Bose, Avinandan, et al.
Pubblicazione: (2024)

Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
di: Bhagwatkar, Rishika, et al.
Pubblicazione: (2025)

Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration
di: Bose, Avinandan, et al.
Pubblicazione: (2024)

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
di: Kazdan, Joshua, et al.
Pubblicazione: (2025)

LoRe: Personalizing LLMs via Low-Rank Reward Modeling
di: Bose, Avinandan, et al.
Pubblicazione: (2025)

LitLLM: A Toolkit for Scientific Literature Review
di: Agarwal, Shubham, et al.
Pubblicazione: (2024)

LitLLMs, LLMs for Literature Review: Are we there yet?
di: Agarwal, Shubham, et al.
Pubblicazione: (2024)

Initializing Services in Interactive ML Systems for Diverse Users
di: Bose, Avinandan, et al.
Pubblicazione: (2023)

PrefDisco: Benchmarking Proactive Personalized Reasoning
di: Li, Shuyue Stella, et al.
Pubblicazione: (2025)

The BrowserGym Ecosystem for Web Agent Research
di: De Chezelles, Thibault Le Sellier, et al.
Pubblicazione: (2024)

InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
di: Sahu, Gaurav, et al.
Pubblicazione: (2024)

Achieving the Tightest Relaxation of Sigmoids for Formal Verification
di: Chevalier, Samuel, et al.
Pubblicazione: (2024)

A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations
di: Nejadgholi, Isar, et al.
Pubblicazione: (2025)

RECAP: Retrieval-Augmented Audio Captioning
di: Ghosh, Sreyan, et al.
Pubblicazione: (2023)

Norm-Bounded Low-Rank Adaptation
di: Wang, Ruigang, et al.
Pubblicazione: (2025)

Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networks
di: Wang, Ruigang, et al.
Pubblicazione: (2024)

Is Behavioral Economics Doomed?
di: K. Levine, David
Pubblicazione: (2018)

Cold-Start Personalization via Training-Free Priors from Structured World Models
di: Bose, Avinandan, et al.
Pubblicazione: (2026)

CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP
di: Evuru, Chandra Kiran Reddy, et al.
Pubblicazione: (2024)

Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems
di: Hoppe, Heiko, et al.
Pubblicazione: (2023)

Deep Learning for Data-Driven Districting-and-Routing
di: Ferraz, Arthur, et al.
Pubblicazione: (2024)

VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
di: Miculicich, Lesly, et al.
Pubblicazione: (2025)

One Color Makes All the Difference in the Tractability of Partial Coloring in Semi-Streaming
di: Das, Avinandan
Pubblicazione: (2026)

Behavioural Cloning in VizDoom
di: Spick, Ryan, et al.
Pubblicazione: (2024)

The Case Against Climate Doom
di: Jakob, Michael
Pubblicazione: (2025)

Is the System of Nation‐States Doomed?
di: Branko Milanovic
Pubblicazione: (2026)

ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds
di: Ghosh, Sreyan, et al.
Pubblicazione: (2024)

FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents
di: Kerboua, Imene, et al.
Pubblicazione: (2025)

MARCO: A Memory-Augmented Reinforcement Framework for Combinatorial Optimization
di: Garmendia, Andoni I., et al.
Pubblicazione: (2024)

An Evaluation of "Choice" as a Selection Tool in the Field of Western History.
di: Boisvert, Marianne
Pubblicazione: (1977)

Knowing When Not to Answer: Evaluating Abstention in Multimodal Reasoning Systems
di: Madhusudhan, Nishanth, et al.
Pubblicazione: (2026)

CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution
di: Kim, Minbeom, et al.
Pubblicazione: (2026)

JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation
di: Nekoei, Hadi, et al.
Pubblicazione: (2025)

ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations
di: Ghosh, Sreyan, et al.
Pubblicazione: (2023)

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs
di: Ghosh, Sreyan, et al.
Pubblicazione: (2024)