Monday, November 16, 2026
Translate
PrivacySubmit newsShare your story Newsletter Advertise
Breaking
Research news

Radar de Pesquisa, 10 de novembro de 2026: 9 novos artigos de IA e segurança para conhecer

As pesquisas mais relevantes sobre IA e segurança da Nature & arXiv, com os resumos dos próprios autores e links para os artigos.

9 papers, Nature & arXiv

Traduzido do inglês pela TechUpscale com ajuda de IA e verificado com o original. Ler o original em inglês

Novas pesquisas sobre IA e segurança, selecionadas pela relevância para modelos de linguagem, agentes de IA e cibersegurança. Os resumos são das próprias palavras dos autores ou da editora, com links para o original.

Revisado por pares

AI-guided human-in-the-loop inverse design of high performance engineering structures

Nature

Novos preprints (ainda não revisados por pares)

META-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM

arXiv · Mahabubur Rahman Miraj, Hongyu Huang, Nankun Mu, Chao Chen, Shanqin Yi

The TechUpscale Brief. The day's cyber, AI and tech news in one short email, every weekday morning. Free. Unsubscribe anytime.

Large Language Models (LLMs) remain vulnerable to jailbreak attacks and harmful-content prompts, particularly under adversarial distribution shifts where static alignment pipelines fail to generalize. Although introspective methods such as STAIR strengthen refusal consistency, they depend on fixed self-evaluation policies that cannot rapidly adapt to evolving manipulation strategies.

Understanding Efficient LLM Serving: An Empirical Study of Frameworks, Optimizations Algorithms, and Real-World Adoption

arXiv · Forough Majidi, Mohammad Mehdi Morovati, Foutse Khomh, Heng Li

Large Language Models (LLMs) are integrated into software systems and AI services, making efficient LLM serving a concern for software engineering. Serving LLMs is challenging because inference requires computation, memory, GPU resources, and execution while maintaining latency and throughput.

MetaPI: Constructing Prompt Injection Benchmarks from LLM Agent Benchmark

arXiv · Peiran Wang, Chong Xiang, Wenjie Qu, Ying Li, Jiaheng Zhang, G. Edward Suh, Yuan Tian

Large language model (LLM) agents increasingly perform complex tasks using high-privilege tools, making indirect prompt injection (IPI) a critical security risk. However, IPI benchmarks lag behind their rapidly evolving utility counterparts, only offering limited task and environment coverage and relying on narrow, static attack scenarios.

Adversarial Evaluation of Large Language Models for Patient-Friendly Radiology Report Summarization

arXiv · Magdalini Paschali, Asad Aali, Arogya Koirala, Andrew Johnston, Katherine McNamara, Richard Gaus, Roxana Daneshjou, David B. Larson, Akshay S. Chaudhari

Purpose: To develop and validate a scalable adversarial evaluation framework for assessing the robustness of large language models (LLMs) that generate patient-friendly summaries of radiology reports. Methods: We introduced a clinically grounded adversarial framework that uses controlled term substitutions and impression removals across intensity levels.

Detecting Shadow AI: Unsanctioned LLM Agents on Enterprise Endpoints: A Taxonomy, an Open Detector and a Controlled Evaluation

arXiv · Jeremy Canale, Fabien Soulis

Shadow IT, the use of technology that the IT organisation has not approved, is a long-standing governance problem. We argue that autonomous AI agents can make it grow much faster: agents make building tools nearly free, act with their user's privileges, and leave behind scripts, automations and MCP servers that are themselves unsanctioned.

Safety Direction Adapter: A Training-Free Post-Hoc Safety Patch for Fine-Tuned Open-Weight LLMs

arXiv · Chansu Han, Takeshi Takahashi

Open-weight LLMs are routinely fine-tuned from public repositories, yet task-specific adaptation can silently erode safety alignment inherited from instruct-tuned bases. This is a supply-chain risk when organizations ship third-party checkpoints without full re-alignment.

CyberBinGym: Can AI Agents Turn Binary Patches into Real Exploits?

arXiv · Lambang Akbar Wijayadi, Zhaoqi Xiao, Zhun Wang, Hongwei Li, Wenbo Guo, Heng Yin, Zhenkai Liang, Dawn Song

Security fixes usually reach users as compiled updates, but deployment delays leave unpatched systems exposed. During this window, comparing patched and unpatched binaries can reveal how to exploit a vulnerability, turning a defensive update into actionable information for attackers.

Enforcing Demographic Coherence: A Harms Aware Framework for Reasoning about Private Data Release

arXiv · Mark Bun, Marco Carmosino, Palak Jain, Gabriel Kaptchuk, Satchit Sivakumar

The technical literature about data privacy largely consists of two complementary approaches: formal definitions of conditions sufficient for privacy preservation and attacks that demonstrate privacy breaches. Differential privacy is an accepted standard in the former sphere.

Add TechUpscale as a preferred source on Google

The TechUpscale Brief

The day's cyber, AI and tech news in one short email, every weekday morning. Free. Unsubscribe anytime.

I'm most interested in

Join the conversation

Comments are moderated. Be civil and stay on the story: no personal attacks, hate, spam or ads, and no one else's private details. Your email is never shown. Privacy policy.

More Research