Can a language model do live adversarial level design? Yes, emphasis on the adversarial part The post I Made an LLM Lay Siege to My Minecraft House appeared first on Towards Data Science .
arXiv:2502. 02260v2 Announce Type: replace Abstract: In the past decade, considerable research effort has been devoted to securing machine learning (ML) models that operate in adversarial settings.
arXiv:2607. 18268v1 Announce Type: new Abstract: Real-world applications that use closed-source large language models (LLMs) need advanced safety measures that go beyond the basic content filters.
The paper investigates how multimodal large language models are more susceptible to prompt injection when adversarial instructions are presented as text rather than as non-textual inputs like images. It proposes a training‑free defense that renders untrusted payloads into typographic images (or audio) before they reach the model, a method called Pictionary. Experiments on ten models and two benchmarks show that this approach significantly lowers attack success rates while maintaining normal functionality, and that fine‑tuning on image‑rendered instructions can further reduce the modality gap.
Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines. In this post we’ll show how adversarial examples work across different mediums, and will discuss why securing systems against them can be difficult.
arXiv:2407. 20242v5 Announce Type: replace-cross Abstract: Embodied AI represents systems where AI is integrated into physical entities.
arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.
arXiv:2508.02312v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine...
The paper introduces DYNASHIELD, a black-box moving target defense for large language models that dynamically customizes decoding hyperparameters and system prompts during inference. It first identifies decoding configurations that lower the probability of successful jailbreak attacks, then samples from a weighted pool of these configurations to add controlled variability to the model’s behavior. Experiments on seven open-source LLMs and four state-of-the-art jailbreak attacks show that DYNASHIELD significantly reduces attack success rates while preserving response quality and adding minimal inference overhead.
This study investigates whether large language models (LLMs) exhibit different safety vulnerabilities when prompted with emojis instead of plain text. By testing 50 emoji‑augmented prompts on four open‑source LLMs—Mistral 7B, Qwen 2 7B, Gemma 2 9B, and Llama 3 8B—the authors found varying success rates of unsafe responses: Gemma 2 9B and Mistral 7B each had a 10% success rate, Llama 3 8B had 6%, while Qwen 2 7B was fully resistant. A chi‑square test confirmed significant differences in the outcome distributions, suggesting that input representation can markedly affect model robustness.
The paper examines the vulnerability of open‑weight large language model safeguards that aim to block harmful usage by assuming new harmful behavior arises only through fine‑tuning. It demonstrates that simple, low‑cost attacks—abliteration and prefilling—can significantly increase attack success rates across multiple benchmarks, and proposes an abliteration‑resistant tuning (ART) method that mitigates these attacks. The study shows that safeguarding defenses must be evaluated against a broader range of attack strategies beyond fine‑tuning.
arXiv:2510.17904v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely used because they process structures, syntax and code well, but this same ability also makes them par...