GeoClip: Geometry-Aware Clipping for Differentially Private SGD

Differentially private stochastic gradient descent DP-SGD is the most widely used method for training machine learning models with provable privacy guarantees. A key challenge in DP-SGD is setting the per-sample gradient clipping threshold, which significantly affects the trade-off between privac...

Versal Adaptive SoC – Overwriting Protected Memory Regions through PLM Firmware

AMD ID: AMD-SB-8010 Potential Impact: Loss of confidentiality and Integrity Severity: Medium Summary In Versal™ Adaptive SoC devices, the Platform Loader and Manager PLM implements runtime post-boot software services that can allow a remote processor to command the PLM to execute cryptographic...

Versal™ Adaptive SoC – Improper Configuration of the Secure Stream Switch during Post-Boot Cryptographic Operations

AMD ID: AMD-SB-8011 Potential Impact: N/A Severity: N/A Summary In Versal™ Adaptive SoC devices, the Platform Loader and Manager PLM implements runtime post-boot software services that allows a remote processor to command the PLM to execute cryptographic operations – including AES, SHA3, RSA, ECD...

Predictive-CSM: Lightweight Fragment Security for 6LoWPAN IoT Networks

Fragmentation is a routine part of communication in 6LoWPAN-based IoT networks, designed to accommodate small frame sizes on constrained wireless links. However, this process introduces a critical vulnerability fragments are typically stored and processed before their legitimacy is confirmed,...

CSVAR: Enhancing Visual Privacy in Federated Learning Via Adaptive Shuffling against Overfitting

Although federated learning preserves training data within local privacy domains, the aggregated model parameters may still reveal private characteristics. This vulnerability stems from clients' limited training data, which predisposes models to overfitting. Such overfitting enables models to...

Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping

Differential privacy DP has become an essential framework for privacy-preserving machine learning. Existing DP learning methods, however, often have disparate impacts on model predictions, e.g., for minority groups. Gradient clipping, which is often used in DP learning, can suppress larger...

Adaptive Privacy-Preserving SSD

Data remanence in NAND flash complicates complete deletion on IoT SSDs. We design an adaptive architecture offering four privacy levels PL0-PL3 that select among address, data, and parity deletion techniques. Quantitative analysis balances efficacy, latency, endurance, and cost. Machine-learning...

Privacy-Preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models

Prompt learning is a crucial technique for adapting pre-trained multimodal language models MLLMs to user tasks. Federated prompt personalization FPP is further developed to address data heterogeneity and local overfitting, however, it exposes personalized prompts - valuable intellectual assets - ...

Efficient Preimage Approximation for Neural Network Certification

The growing reliance on artificial intelligence in safety- and security-critical applications demands effective neural network certification. A challenging real-world use case is certification against patch attacks'', where adversarial patches or lighting conditions obscure parts of images, for...

Semantic-Preserving Adversarial Attacks on LLMs: an Adaptive Greedy Binary Search Approach

Large Language Models LLMs increasingly rely on automatic prompt engineering in graphical user interfaces GUIs to refine user inputs and enhance response accuracy. However, the diversity of user requirements often leads to unintended misinterpretations, where automated optimizations distort...

Fedora: Security Advisory (FEDORA-2024-7bc1df53fc)

The remote host is missing an update for the SPDX-FileCopyrightText: 2025 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only ifdescription...

Parallel Kac'S Walk Generates PRU

Ma and Huang recently proved that the PFC construction, introduced by Metger, Poremba, Sinha and Yuen MPSY24, gives an adaptive-secure pseudorandom unitary family PRU. Their proof developed a new path recording technique MH24. In this work, we show that a linear number of sequential repetitions o...

Co-Evolutionary Dynamics of Attack and Defence in Cybersecurity

In the evolving digital landscape, it is crucial to study the dynamics of cyberattacks and defences. This study uses an Evolutionary Game Theory EGT framework to investigate the evolutionary dynamics of attacks and defences in cyberspace. We develop a two-population asymmetric game between attack...

$PD^3F$: a Pluggable and Dynamic DoS-Defense Framework against Resource Consumption Attacks Targeting Large Language Models

Large Language Models LLMs, due to substantial computational requirements, are vulnerable to resource consumption attacks, which can severely degrade server performance or even cause crashes, as demonstrated by denial-of-service DoS attacks designed for LLMs. However, existing works lack mitigati...

CVE-2024-31230

Missing Authorization vulnerability in ShortPixel ShortPixel Adaptive Images shortpixel-adaptive-images.This issue affects ShortPixel Adaptive Images: from n/a through = 3.8.2...

CVE-2024-35172

Server-Side Request Forgery SSRF vulnerability in ShortPixel ShortPixel Adaptive Images shortpixel-adaptive-images.This issue affects ShortPixel Adaptive Images: from n/a through = 3.8.3...

CVE-2024-4689

Cross-Site Request Forgery CSRF vulnerability in ShortPixel ShortPixel Adaptive Images shortpixel-adaptive-images.This issue affects ShortPixel Adaptive Images: from n/a through = 3.8.3...

CVE-2024-20481

A vulnerability in the Remote Access VPN RAVPN service of Cisco Adaptive Security Appliance ASA Software and Cisco Firepower Threat Defense FTD Software could allow an unauthenticated, remote attacker to cause a denial of service DoS of the RAVPN service. This vulnerability is due to resource...

CVE-2024-20359

A vulnerability in a legacy capability that allowed for the preloading of VPN clients and plug-ins and that has been available in Cisco Adaptive Security Appliance ASA Software and Cisco Firepower Threat Defense FTD Software could allow an authenticated, local attacker to execute arbitrary code...

CVE-2024-20331

A vulnerability in the session authentication functionality of the Remote Access SSL VPN feature of Cisco Adaptive Security Appliance ASA Software and Cisco Firepower Threat Defense FTD Software could allow an unauthenticated, remote attacker to prevent users from authenticating. This vulnerabili...