Related papers: Unsafe Impedance: Safe Languages and Safe by Desig…
Large language models (LLMs) have become indispensable for automated code generation, yet the quality and security of their outputs remain a critical concern. Existing studies predominantly concentrate on adversarial attacks or inherent…
In this paper, we present a new semantics to check file safety of multithreaded programs. A file-safe program is one that reaches a final configuration under the proposed semantics. We extend the While language with file operations and…
Language-based ecosystems (LBE), i.e., software ecosystems based on a single programming language, are very common. Examples include the npm ecosystem for JavaScript, and PyPI for Python. These environments encourage code reuse between…
Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…
Information protection is becoming a focal point for designing, creating and implementing software applications within highly integrated technology environments. The use of a safe coding technique in the software development process is…
Recent secure code generation methods, using vulnerability-aware fine-tuning, prefix-tuning, and prompt optimization, claim to prevent LLMs from producing insecure code. However, their robustness under adversarial conditions remains…
As the use of large language model (LLM) agents continues to grow, their safety vulnerabilities have become increasingly evident. Extensive benchmarks evaluate various aspects of LLM safety by defining the safety relying heavily on general…
Attracted by the impressive power of Multimodal Large Language Models (MLLMs), the public is increasingly utilizing them to improve the efficiency of daily work. Nonetheless, the vulnerabilities of MLLMs to unsafe instructions bring huge…
When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…
This paper addresses a challenging interactive task learning scenario we call rearrangement under unawareness: an agent must manipulate a rigid-body environment without knowing a key concept necessary for solving the task and must learn…
Violence is an epidemic in Brazil and a problem on the rise world-wide. Mobile devices provide communication technologies which can be used to monitor and alert about violent situations. However, current solutions, like panic buttons or…
Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images. However, ensuring the safety of these models remains a significant challenge,…
Given programming languages can provide different types and levels of security support, it is critically important to consider security aspects while selecting programming languages for developing software systems. Inadequate consideration…
Program obfuscation is a widely employed approach for software intellectual property protection. However, general obfuscation methods (e.g., lexical obfuscation, control obfuscation) implemented in mainstream obfuscation tools are heuristic…
The Rust programming language restricts aliasing to provide static safety guarantees. However, in certain situations, developers need to bypass these guarantees by using a set of unsafe features. If they are used incorrectly, these features…
Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…
Safety-aligned language models often exhibit fragile and imbalanced safety mechanisms, increasing the likelihood of generating unsafe content. In addition, incorporating new knowledge through editing techniques to language models can…
The widespread adoption and increasing prominence of large language models (LLMs) in global technologies necessitate a rigorous focus on ensuring their safety across a diverse range of linguistic and cultural contexts. The lack of a…
Software engineers in various industrial domains are already using Large Language Models (LLMs) to accelerate the process of implementing parts of software systems. When considering its potential use for ADAS or AD systems in the automotive…
Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…