Patcher: Post-Hoc Patching of Backdoored Large Language Models

Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms. Existing defenses often require comprehensive attack information or multiple triggered examples, making them impractical wh...

Astra Linux - уязвимость в linux-5.10

In the Linux kernel, the following vulnerability has been resolved: bpf: Fixed an improper scalar handling in the maybeforkscalars function for BPFOR. The maybeforkscalars function is called for both BPFAND and BPFOR when the source operand is a constant. When dst has a signed range of -1, 0, it...

Set Shaping Theory As a Complementary Payload-Shaping Layer for Steganography

This paper studies the use of Set Shaping Theory SST as a reversible payload-shaping layer for least significant bit LSB image steganography. The proposal is not intended to replace existing steganographic methods or to compete with them as a new embedding scheme. Instead, SST is positioned as a...

CVE-2026-44497 ZEBRA: Consensus Divergence in Transparent Sighash Hash-Type Handling due to Stale Buffer

ZEBRA is a Zcash node written entirely in Rust. Prior to zebrad version 4.4.0 and prior to zebra-script version 6.0.0, the fix for CVE-2026-41583 introduced a separate issue due to insufficient error handling of the case where the sighash type is invalid, during sighash computation. Instead of...

CVE-2026-41583 ZEBRA: Consensus Divergence in Transparent Sighash Hash-Type Handling

ZEBRA is a Zcash node written entirely in Rust. Prior to zebrad version 4.3.1 and prior to zebra-script version 5.0.2, after a refactoring, Zebra failed to validate a consensus rule that restricted the possible values of sighash hash types for V5 transactions which were enabled in the NU5 network...

Zebra's Transparent SIGHASH_SINGLE Handling Diverges from zcashd for Corresponding Outputs

Zebra Transparent SIGHASHSINGLE Corresponding-Output Handling Diverges From zcashd Summary For V5+ transparent spends, Zebra and zcashd disagree on the same consensus rule: SIGHASHSINGLE must fail when the input index has no corresponding output. zcashd treats this as consensus-invalid under...

GHSA-GQ4H-3GRW-2RHV Zebra has Consensus Divergence in Transparent Sighash Hash-Type Handling due to Stale Buffer

CVE-2026-44497: Consensus Divergence in Transparent Sighash Hash-Type Handling due to Stale Buffer Summary The fix for https://github.com/ZcashFoundation/zebra/security/advisories/GHSA-8m29-fpq5-89jj introduced a separate issue due to insuficient error handling of the case where the sighash type ...

Zebra has Consensus Divergence in Transparent Sighash Hash-Type Handling due to Stale Buffer

CVE-2026-44497: Consensus Divergence in Transparent Sighash Hash-Type Handling due to Stale Buffer Summary The fix for https://github.com/ZcashFoundation/zebra/security/advisories/GHSA-8m29-fpq5-89jj introduced a separate issue due to insuficient error handling of the case where the sighash type ...

resource-agents security update

4.9.0-54.33 - bundled pyasn1: fix CVE-2026-30922 Resolves: RHEL-157190 4.9.0-54.32 - db2: do not use db2stop to avoid divergence in the log Resolves: RHEL-166181 4.9.0-54.31 - db2: set reintegration when promotion is successful Resolves: RHEL-153157...

Information Theoretic Adversarial Training of Large Language Models

Large language models LLMs remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing approaches are computationally expensive and difficult to...

CVE-2026-35370

The id utility in uutils coreutils miscalculates the groups= section of its output. The implementation uses a user's real GID instead of their effective GID to compute the group list, leading to potentially divergent output compared to GNU coreutils. Because many scripts and automated processes...

GHSA-Q94G-3GCF-66X7 uutils coreutils has an Incorrect Authorization issue

The id utility in uutils coreutils miscalculates the groups= section of its output. The implementation uses a user's real GID instead of their effective GID to compute the group list, leading to potentially divergent output compared to GNU coreutils. Because many scripts and automated processes...

CVE-2026-35375

CVE-2026-35375 concerns the uutils coreutils split utility, where a logic error causes output filenames to be corrupted when given non-UTF-8 prefixes/suffixes. The code uses to_string_lossy() to build chunk filenames, which rewrites invalid bytes as the UTF-8 replacement character (U+FFFD). Unlik...

CVE-2026-35370 uutils coreutils id Incorrect Access-Control Decisions via Misrepresented Group Membership

The id utility in uutils coreutils miscalculates the groups= section of its output. The implementation uses a user's real GID instead of their effective GID to compute the group list, leading to potentially divergent output compared to GNU coreutils. Because many scripts and automated processes...

CVE-2026-35370

The id utility in uutils coreutils miscalculates the groups= section of its output. The implementation uses a user's real GID instead of their effective GID to compute the group list, leading to potentially divergent output compared to GNU coreutils. Because many scripts and automated processes...

PT-2026-34506

The id utility in uutils coreutils miscalculates the groups= section of its output. The implementation uses a user's real GID instead of their effective GID to compute the group list, leading to potentially divergent output compared to GNU coreutils. Because many scripts and automated processes...

PT-2026-33826

NEMU OpenXiangShan/NEMU before v2025.12.r2 contains an improper instruction-validation flaw in its RISC-V Vector RVV decoder. The decoder does not correctly validate the funct3 field when decoding vsetvli/vsetivli/vsetvl, allowing certain invalid OP-V instruction encodings to be misinterpreted an...

Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems

Rowhammer on GPU DRAM has enabled adversarial bit flips in model weights; shared KV-cache blocks in LLM serving systems present an analogous but previously unexamined target. In vLLM's Prefix Caching, these blocks exist as a single physical copy without integrity protection. Using software fault...

Zebra Vulnerable to Consensus Divergence in Transparent Sighash Hash-Type Handling

CVE-2026-41583: Consensus Divergence in Transparent Sighash Hash-Type Handling Summary After a refactoring, Zebra failed to validate a consensus rule that restricted the possible values of sighash hash types for V5 transactions which were enabled in the NU5 network upgrade. Zebra nodes could thus...

Linux Distros Unpatched Vulnerability : CVE-2026-31413

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: bpf: Fix unsound scalar forking in maybeforkscalars for BPFOR maybeforkscalars is called for...