Tootfinder

Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal
Yang Wang, Chenghao Xiao, Yizhi Li, Stuart E. Middleton, Noura Al Moubayed, Chenghua Lin
https://arxiv.org/abs/2507.21750

Adversarial Defence without Adversarial Defence: Enhancing Language Model Robustness via Instance-level Principal Component Removal
Pre-trained language models (PLMs) have driven substantial progress in natural language processing but remain vulnerable to adversarial attacks, raising concerns about their robustness in real-world applications. Previous studies have sought to mitigate the impact of adversarial attacks by introducing adversarial perturbations into the training process, either implicitly or explicitly. While both strategies enhance robustness, they often incur high computational costs. In this work, we propose …

The Federal Trade Commission, last month, announced that it would approve the merger of two of the biggest ad agencies in the world
-- only if the parties agree to an unusual condition:
The merged company cannot refuse to place ads on websites for political reasons.
The move was a sharp break from its traditional practice.
The F.T.C. is usually focused on such concerns as consumer protection and monopoly power;
Now it’s trying to dictate where businesses adverti…

Opinion | Trump’s Campaign to Coerce Advertisers Into Backing Conservative Media
The administration seeks to coerce advertisers into using conservative media.

Sources: Anthropic has been lobbying Congress to oppose a bill banning states from regulating AI, and pushed against the recent US AI deal with Gulf states (Reed Albergotti/Semafor)
https://www.semafor.com/article/05/30/2025/anthropi…

Anthropic emerges as an adversary to Trump’s big bill
Sources familiar say the White House, angered by Anthropic’s lobbying against its chief piece of legislation, have come to view the AI company as an obstacle.

Tesla nimmt Model X und Model S in Deutschland aus dem Programm
Tesla hat seine Oberklasse-Modelle Model S und X in Deutschland aus dem Konfigurator genommen. Damit bietet der US-Autobauer hier nur noch Model 3 und Y an.

Und warum genau steht da nicht: „Autofahrende, mit viel Abstand überholen!“ ???
#AutofahrerBrille #AutoJustiz #AutoInfrastruktur

Disney says it has completed its 2025-2026 Upfronts with streaming accounting for more than 40% of total volume and sports advertising nearing $4B (Jill Goldsmith/Deadline)
https://deadline.com/2025/07/disney-wraps-upfront-sports-advertising-live-…

Disney Wraps Upfront With Sports Advertising Near $4B, Overall Volume Flat
Disney Advertising completed its 2025-2026 Upfront with overall volume flat from year before, despite increased sales in sports and streaming.

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
Chunlong Xie, Jialing He, Shangwei Guo, Jiacheng Wang, Shudong Zhang, Tianwei Zhang, Tao Xiang
https://arxiv.org/abs/2505.23266

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
We present Adversarial Object Fusion (AdvOF), a novel attack framework targeting vision-and-language navigation (VLN) agents in service-oriented environments by generating adversarial 3D objects. While foundational models like Large Language Models (LLMs) and Vision Language Models (VLMs) have enhanced service-oriented navigation systems through improved perception and decision-making, their integration introduces vulnerabilities in mission-critical service workflows. Existing adversarial attac…

ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models
Hyun Jun Yook, Ga San Jhun, Jae Hyun Cho, Min Jeon, Donghyun Kim, Tae Hyung Kim, Youn Kyu Lee
https://arxiv.org/abs/2507.21985

ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models
Machine unlearning (MU) removes specific data points or concepts from deep learning models to enhance privacy and prevent sensitive content generation. Adversarial prompts can exploit unlearned models to generate content containing removed concepts, posing a significant security risk. However, existing adversarial attack methods still face challenges in generating content that aligns with an attacker's intent while incurring high computational costs to identify successful prompts. To address th…

Interactive Adversarial Testing of Autonomous Vehicles with Adjustable Confrontation Intensity
Yicheng Guo, Chengkai Xu, Jiaqi Liu, Hao Zhang, Peng Hang, Jian Sun
https://arxiv.org/abs/2507.21814

Interactive Adversarial Testing of Autonomous Vehicles with Adjustable Confrontation Intensity
Scientific testing techniques are essential for ensuring the safe operation of autonomous vehicles (AVs), with high-risk, highly interactive scenarios being a primary focus. To address the limitations of existing testing methods, such as their heavy reliance on high-quality test data, weak interaction capabilities, and low adversarial robustness, this paper proposes ExamPPO, an interactive adversarial testing framework that enables scenario-adaptive and intensity-controllable evaluation of auto…

Radio Adversarial Attacks on EMG-based Gesture Recognition Networks
Hongyi Xie
https://arxiv.org/abs/2507.21387 https://arxiv.org/pdf/2507.21387

Radio Adversarial Attacks on EMG-based Gesture Recognition Networks
Surface electromyography (EMG) enables non-invasive human-computer interaction in rehabilitation, prosthetics, and virtual reality. While deep learning models achieve over 97% classification accuracy, their vulnerability to adversarial attacks remains largely unexplored in the physical domain. We present ERa Attack, the first radio frequency (RF) adversarial method targeting EMG devices through intentional electromagnetic interference (IEMI). Using low-power software-defined radio transmitters,…