7 papers · 1 filter
FieldFormer: Locality-Aware Transformers for Spatio-Temporal Modeling on Sparse Sensor Networks
Ankit Bhardwaj, Ananth Balashankar, Lakshminarayanan Subramanian
Spatio-temporal sensor data in real-world systems is often sparse, noisy, and irregular, making latent field reconstruction fundamentally underconstrained. Under extreme sparsity,…
Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddings
Fatemeh Akbarian, Anahita Baninajjar, Yingyi Zhang +2
Multi-modal foundation models align images, text, and other modalities in a shared embedding space but remain vulnerable to adversarial illusions [35], where imperceptible perturba…
Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
Xiangwen Wang, Ananth Balashankar, Varun Chandrasekaran
Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, mode…
Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges
Chen Feng, Minghe Shen, Ananth Balashankar +2
Reliable certification of Large Language Models (LLMs)-verifying that failure rates are below a safety threshold-is critical yet challenging. While "LLM-as-a-Judge" offers scalabil…
Adversarial Reinforcement Learning for Large Language Model Agent Safety
Zizhao Wang, Dingcheng Li, Vaishakh Keshava +4
Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, wh…
InfAlign: Inference-aware language model alignment
Ananth Balashankar, Ziteng Sun, Jonathan Berant +9
Language model alignment is a critical step in training modern generative language models. Alignment targets to improve win rate of a sample from the aligned model against the base…