On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “red-teaming”

Red-Teaming Text-to-Image Systems by Rule-based Preference Modelingcs.LG

Proposes RPG-RT for red-teaming T2I models without internal access.

problem Evaluating T2I models' security through red-teaming is challenging due to their closed-source nature and unknown defense mechanisms.

method Integrates LLM and rule-based preference modeling to dynamically adapt to unknown defense mechanisms.

result Demonstrates superior and practical approach for red-teaming T2I models.

text-to-image red-teaming rule-based preference modeling dynamic adaptation unknown defense mechanisms

2025-05-27abs ↗pdf ↗

Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Servicesq-fin.CP

New framework assesses LLM security risks in BFSI.

problem Lack of domain-specific security evaluation for LLMs in BFSI.

method Risk-aware evaluation framework combining taxonomy, automated red-teaming, and ensemble judging.

result Higher decoding stochasticity and adaptive interaction lead to more severe disclosures.

LLMs BFSI Red Teaming Security Evaluation Risk Assessment

2026-03-11abs ↗pdf ↗

Probabilistic Inference in Language Models via Twisted Sequential Monte Carlocs.LG

We use SMC with twist functions to improve probabilistic inference in LLMs.

problem Improving probabilistic inference in large language models.

method We use Sequential Monte Carlo with learned twist functions to estimate expected future values and focus inference on promising sequences.

result Twisted SMC improves the accuracy of language model inference and evaluation.

Sequential Monte Carlo Language Models Probabilistic Inference Twist Functions Soft Reinforcement Learning

2024-04-26abs ↗pdf ↗

Online Safety Monitoring for LLMscs.AI

Simple online monitor detects unsafe LLM outputs.

problem LLMs generate unsafe outputs despite training.

method Thresholding external verifier signal to decide alarms.

result Simple design competitive with advanced methods.

LLM safety online monitoring thresholding risk control

2026-07-02abs ↗pdf ↗

Anomaly Detection in Large Scale Networks with Latent Space Modelsstat.ME

We develop a real-time anomaly detection algorithm for directed activity on large, sparse networks. We model the propensity for future activity using a dynamic logistic model with interaction terms for sender- and receiver-specific latent factors in addition to sender- and receiver-specific popularity scores; deviation…

2019-11-13abs ↗pdf ↗

Diffusion LLMs are Natural Adversaries for any LLMcs.LG

Diffusion LLMs can efficiently generate harmful prompts for adversarial testing.

problem Generating harmful prompts for adversarial testing is resource-intensive and costly.

method Transformed adversarial prompt optimization into an efficient inference task using pretrained Diffusion LLMs.

result Only a few conditional samples are required to generate harmful prompts with high reward.

Diffusion LLMs Adversarial Testing Prompt Optimization Generative Models Harmful Prompts

2025-10-31abs ↗pdf ↗

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Modelscs.CR

VERA-V uses variational inference to discover vulnerabilities in multimodal vision-language models.

problem Existing methods for jailbreaking vision-language models are brittle, limited, and focus on single attacks.

method VERA-V recasts jailbreak discovery as learning a joint posterior distribution over text-image prompts, using variational inference and three complementary strategies.

result VERA-V consistently outperforms state-of-the-art baselines, achieving up to 53.75% higher attack success rate.

vision-language models variational inference jailbreaking multimodal attacks language models

2025-10-20abs ↗pdf ↗