the State Backdoor
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
arXiv:2601.04266v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics. However, their complex multimodal interactions also expose new security vulnerabilities. In this paper, we investigate a backdoor threat in VLA models, where malicious inputs cause targeted misbehavior while preserving performance on clean data.
Backdooring Masked Diffusion Language Models
arXiv:2605.19262v2 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive language models do not directly apply to MDLMs because MDLMs rely on discrete state corruption and iterative denoising rather than continuous noising or left-to-right prediction. In this work, we present...
Targeting World Models to Compromise Robot Learning Pipelines
arXiv:2606.09499v1 Announce Type: new Abstract: World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data or simulating real world environments, with many works proposing their integration into the robot learning pipeline. While highly practical, in this work we demonstrate that world models introduce a uniquely stealthy and effective data poisoning entry point into the robot learning supply chain...
BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
arXiv:2605.31246v1 Announce Type: new Abstract: Prompt learning is a new machine learning paradigm that has attracted ample attention due to its simplicity and proven efficacy. Despite its growing adoption, the security vulnerabilities associated with this paradigm remain underexplored. In this work, we take the first step to propose BadBone, a stealthy and adaptive backdoor attack against prompt learning using bi-level optimization.
Cryptographic Backdoor for Neural Networks: Boon and Bane
arXiv:2509.20714v2 Announce Type: replace Abstract: In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as well as in presenting the defenses as well. On the attack side, a carefully planted cryptographic backdoor enables powerful and invisible attack on the NN. Considering the defense, we present applications:
From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors
Announce Type: new Abstract: LLM agents are evolving from conversational chatbots to operational tools in real-world workspaces. In local agentic harnesses, an LLM can read and write files, call tools, and reuse workspace state across sessions. While such capabilities enhance utility, they also expose a new attack surface for attackers.
Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
Announce Type: replace Abstract: The expansion of text-to-image diffusion models has raised concerns about harmful outputs, from fabricated depictions of public figures to sexually explicit imagery. To mitigate such risks, prior work has proposed concept erasure methods that aim to sever unwanted concepts from the model via fine-tuning, yet it remains unclear whether these approaches truly remove all links to the harmful concept or merely conceal superficial connections. In this work, we...
India news: Myanmar president arrives to boost ties
India news: Myanmar president arrives to boost ties Published May 30, 2026last updated May 30, 2026What you need to know - Myanmar's president is set to meet with Indian Prime Minister Narendra Modi - The Congress Party is meeting to form a new Cabinet in Karnataka state Here is a roundup of some of the top headlines that have India talking on Saturday, May 30: Tired of missing our real-time updates?Click here to add us as a Preferred Source on Google.
I'm Ohio's state auditor — Medicaid fraud is not just a Washington problem
When I testify on Capitol Hill, I’ll be addressing the fact that my home state of Ohio is not immune to the sophisticated fraud and abuse plaguing Medicaid and other government programs nationally. Wherever there are big government programs backed by big government spending, there will be people who find ways to exploit loopholes and lax controls to fill their own pocketbooks. Left unaddressed by the state bureaucracies, these weaknesses invite outside manipulation and erode public trust.