Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models

Modern large language models LLMs are typically secured by auditing data, prompts, and refusal policies, while treating the forward pass as an implementation detail. We show that intermediate activations in decoder-only LLMs form a vulnerable attack surface for behavioral control. Building on...

EUVD-2025-13173

Malicious code in bioql PyPI...

EUVD-2022-47140

Malicious code in bioql PyPI...

Linux Distros Unpatched Vulnerability : CVE-2021-47592

"The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: net: stmmac: fix tc flower deletion for VLAN priority Rx steering To replicate the issue:- ...

Secure One-Sided Device-Independent Quantum Key Distribution under Collective Attacks with Enhanced Robustness

We study the security of a quantum key distribution QKD protocol under the one-sided device-independent 1sDI setting, which assumes trust in only one party's measurement device. This approach effectively provides a balance between the experimental viability of device-dependent DD-QKD and the...

A Mixture of Linear Corrections Generates Secure Code

Large language models LLMs have become proficient at sophisticated code-generation tasks, yet remain ineffective at reliably detecting or avoiding code vulnerabilities. Does this deficiency stem from insufficient learning about code vulnerabilities, or is it merely a result of ineffective...

Probing the Robustness of Large Language Models Safety to Latent Perturbations

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We argue that this stems from the shallow nature of existing...

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint

As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable use. Recently, activation steering has emerged as an effective approach for enhancing LLM safety by adding a refusal...

The vulnerability of the dr_domain_add_vport_cap() function in the drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c file of the Linux kernel allows a hacker to cause a service failure.

The vulnerability of the drdomainaddvportcap function in the drivers/net/ethernet/mellanox/mlx5/core/steering/sws/drdomain.c file of the Linux kernel is related to the assignment of a null pointer. Exploiting this vulnerability could allow an attacker to cause a service failure...

CVE-2022-44190

Netgear R7000P V1.3.1.64 is vulnerable to Buffer Overflow via parameter enablebandsteering...

SUSE CVE-2023-53079

In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Fix steering rules cleanup vport's mc, uc and multicast rules are not deleted in teardown path when EEH happens. Since the vport's promisc settingsuc, mc and all in firmware are reset after EEH, mlx5 driver will try to...

Rogue Cell: Adversarial Attack and Defense in Untrusted O-RAN Setup Exploiting the Traffic Steering XApp

The Open Radio Access Network O-RAN architecture is revolutionizing cellular networks with its open, multi-vendor design and AI-driven management, aiming to enhance flexibility and reduce costs. Although it has many advantages, O-RAN is not threat-free. While previous studies have mainly examined...

DEBIAN-CVE-2023-53079

In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Fix steering rules cleanup vport's mc, uc and multicast rules are not deleted in teardown path when EEH happens. Since the vport's promisc settingsuc, mc and all in firmware are reset after EEH, mlx5 driver will try to...

CVE-2023-53079 net/mlx5: Fix steering rules cleanup

In the Linux kernel, the following vulnerability has been resolved: net/mlx5: Fix steering rules cleanup vport's mc, uc and multicast rules are not deleted in teardown path when EEH happens. Since the vport's promisc settingsuc, mc and all in firmware are reset after EEH, mlx5 driver will try to...

SUSE CVE-2025-21981

In the Linux kernel, the following vulnerability has been resolved: ice: fix memory leak in aRFS after reset Fix aRFS accelerated Receive Flow Steering structures memory leak by adding a checker to verify if aRFS memory is already allocated while configuring VSI. aRFS objects are allocated in two...

DEBIAN-CVE-2025-21981

In the Linux kernel, the following vulnerability has been resolved: ice: fix memory leak in aRFS after reset Fix aRFS accelerated Receive Flow Steering structures memory leak by adding a checker to verify if aRFS memory is already allocated while configuring VSI. aRFS objects are allocated in two...

UBUNTU-CVE-2025-21981

In the Linux kernel, the following vulnerability has been resolved: ice: fix memory leak in aRFS after reset Fix aRFS accelerated Receive Flow Steering structures memory leak by adding a checker to verify if aRFS memory is already allocated while configuring VSI. aRFS objects are allocated in two...

CVE-2025-21981 ice: fix memory leak in aRFS after reset

In the Linux kernel, the following vulnerability has been resolved: ice: fix memory leak in aRFS after reset Fix aRFS accelerated Receive Flow Steering structures memory leak by adding a checker to verify if aRFS memory is already allocated while configuring VSI. aRFS objects are allocated in two...

CVE-2025-21981

CVE-2025-21981 corresponds to a memory-leak in the Linux kernel ice driver (aRFS) triggered during VSI reconfiguration after reset. The leak arises when VSI reconfiguration allocates aRFS resources again without releasing prior allocations, leading to unreferenced kmemleak entries (e.g., 8192-byt...

kernel: net/mlx5e: Prevent deadlock while disabling aRFS

A flaw was found in the Linus Kernel. A potential deadlock can occur while disabling aRFS in drivers/net/ethernet/mellanox/mlx5/core/enarfs.c...