SAFER-D: a Self-Adaptive Security Framework for Distributed Computing Architectures

The rise of the Internet of Things and Cyber-Physical Systems has introduced new challenges on ensuring secure and robust communication. The growing number of connected devices increases network complexity, leading to higher latency and traffic. Distributed computing architectures DCAs have gaine...

The Hitchhiker'S Guide to Efficient, End-To-End, and Tight DP Auditing

This paper systematizes research on auditing Differential Privacy DP techniques, aiming to identify key insights into the current state of the art and open challenges. First, we introduce a comprehensive framework for reviewing work in the field and establish three cross-contextual desiderata tha...

Rubber Mallet: a Study of High Frequency Localized Bit Flips and Their Impact on Security

The increasing density of modern DRAM has heightened its vulnerability to Rowhammer attacks, which induce bit flips by repeatedly accessing specific memory rows. This paper presents an analysis of bit flip patterns generated by advanced Rowhammer techniques that bypass existing hardware defenses...

LS Electric GMWin 4

RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to disclose information or execute arbitrary code. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of these vulnerabilities, such as: Minimize...

Eval Injection

Overview letta is a Create LLM agents with long-term memory and custom tools Affected versions of this package are vulnerable to Eval Injection via the functionmessage process. An attacker can execute arbitrary code by manipulating the functionname or functionargs arguments. Remediation There is ...

CVE-2025-6101

A vulnerability classified as critical has been found in letta-ai letta up to 0.4.1. Affected is the function functionmessage of the file letta/letta/interface.py. The manipulation of the argument functionname/functionargs leads to improper neutralization of directives in dynamically evaluated...

CVE-2025-6101 letta-ai letta interface.py function_message eval injection

A vulnerability classified as critical has been found in letta-ai letta up to 0.4.1. Affected is the function functionmessage of the file letta/letta/interface.py. The manipulation of the argument functionname/functionargs leads to improper neutralization of directives in dynamically evaluated...

Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications

Recent advancements in LLMs indicate potential for novel applications, e.g., through reasoning capabilities in the latest OpenAI and DeepSeek models. For applying these models in specific domains beyond text generation, LLM-based multi-agent approaches can be utilized that solve complex tasks by...

letta-ai letta 安全漏洞

Letta-ai letta is a stateful agent framework with memory, inference, and context management in the Letta-ai open source. A security vulnerability exists in letta-ai letta version 0.4.1 and earlier, which stems from a dynamic code evaluation malpractice issue that could lead to the execution of...

Chain-Of-Code Collapse: Reasoning Failures in LLMs Via Adversarial Prompting in Code Generation

Large Language Models LLMs have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis -- especially when aided by reasoning tokens and Chain-of-Thought prompting. Yet, a core question remains: do these...

SoK: Evaluating Jailbreak Guardrails for Large Language Models

Large Language Models LLMs have achieved remarkable progress, but their deployment has exposed critical vulnerabilities, particularly to jailbreak attacks that circumvent safety mechanisms. Guardrails--external defense mechanisms that monitor and control LLM interaction--have emerged as a promisi...

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods

In this work, we show that some machine unlearning methods may fail when subjected to straightforward prompt attacks. We systematically evaluate eight unlearning techniques across three model families, and employ output-based, logit-based, and probe analysis to determine to what extent supposedly...

LLMs Cannot Reliably Judge (Yet?): a Comprehensive Assessment on the Robustness of LLM-As-A-Judge

Large Language Models LLMs have demonstrated remarkable intelligence across various tasks, which has inspired the development and widespread adoption of LLM-as-a-Judge systems for automated model testing, such as red teaming and benchmarking. However, these systems are susceptible to adversarial...

EulerOS 2.0 SP12 : libxslt (EulerOS-SA-2025-1600)

According to the versions of the libxslt package installed, the EulerOS installation on the remote host is affected by the following vulnerabilities : numbers.c in libxslt before 1.1.43 has a use-after-free because, in nested XPath evaluations, an XPath context node can be modified but never...

SinoTrack GPS Receiver

RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to access device profiles for which they are not authorized through the common web management interface. Access to the device profile may allow an attacker to perform some remote functions on connected...

Your Agent Can Defend Itself against Backdoor Attacks

Despite their growing adoption across domains, large language model LLM-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific...

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings

Federated learning FL enables collaborative model training among multiple clients without the need to expose raw data. Its ability to safeguard privacy, at the heart of FL, has recently been a hot-button debate topic. To elaborate, several studies have introduced a type of attacks known as gradie...

n8n Workflow Expression Remote Code Execution

This module exploits a critical remote code execution vulnerability CVE-2025-68613 in the n8n workflow automation platform. The vulnerability exists in the workflow expression evaluation system where user-supplied expressions enclosed in are evaluated in an execution context that is not...

SoK: Machine Unlearning for Large Language Models

Large language model LLM unlearning has become a critical topic in machine learning, aiming to eliminate the influence of specific training data or knowledge without retraining the model from scratch. A variety of techniques have been proposed, including Gradient Ascent, model editing, and...

Authorino Uncontrolled Resource Consumption vulnerability

A Developer persona can bring down the Authorino service, preventing the evaluation of all AuthPolicies on the cluster...