BTC $55865.7639
ETH $3222.4858
BNB $400.6682
SOL $110.6842
XRP $0.5548
ADA $0.6230
AVAX $39.2767
DOGE $0.0896
TRX $0.1404
wstETH $3751.1765
LINK $19.0474
DOT $8.0594
WETH $3236.9354
MATIC $1.0625
UNI $10.5983
WBTC $55965.3668
IMX $3.3901
ICP $13.0143
BCH $300.6764
LTC $74.8911
CAKE $3.2355
FIL $8.1517
ETC $28.1561
RNDR $7.4096
KAS $0.1718
DAI $0.9979
HBAR $0.1117
ATOM $11.3293
VET $0.0491
INJ $36.5642
TON $2.1072
OKB $51.3395
LDO $3.5443
FDUSD $1.0015
STX $3.0723
ARB $1.9162
NEAR $4.0168
XMR $131.7677
TIA $17.0755
XLM $0.1186
GRT $0.2823
ENS $22.2643
THETA $2.1117
MKR $2155.4331
WEMIX $2.1023
APEX $2.4575
BEAM $0.0357
BTC $55865.7639
ETH $3222.4858
BNB $400.6682
SOL $110.6842
XRP $0.5548
ADA $0.6230
AVAX $39.2767
DOGE $0.0896
TRX $0.1404
wstETH $3751.1765
LINK $19.0474
DOT $8.0594
WETH $3236.9354
MATIC $1.0625
UNI $10.5983
WBTC $55965.3668
IMX $3.3901
ICP $13.0143
BCH $300.6764
LTC $74.8911
CAKE $3.2355
FIL $8.1517
ETC $28.1561
RNDR $7.4096
KAS $0.1718
DAI $0.9979
HBAR $0.1117
ATOM $11.3293
VET $0.0491
INJ $36.5642
TON $2.1072
OKB $51.3395
LDO $3.5443
FDUSD $1.0015
STX $3.0723
ARB $1.9162
NEAR $4.0168
XMR $131.7677
TIA $17.0755
XLM $0.1186
GRT $0.2823
ENS $22.2643
THETA $2.1117
MKR $2155.4331
WEMIX $2.1023
APEX $2.4575
BEAM $0.0357
  • Catalog
  • Blog
  • Tor Relay
  • Jabber
  • One-Time notes
  • Temp Email
  • What is TOR?
  • We are in tor
  • Scientists conducted the world's first cyberattack using artificial intelligence


    A team of scientists has demonstrated a new attack using the Text-to-SQL model to generate malicious code that can allow an attacker to collect sensitive information and conduct DoS attacks.

    To better interact with users, database applications use artificial intelligence techniques that can translate human queries into SQL queries (Text-to-SQL model), according to the researchers.

    By sending special requests, an attacker can fool the text-to-SQL transformation models to create malicious code. Since such code is automatically executed in the database, it can lead to data leakage to the dark web and DoS attacks.

    The findings, which were confirmed by two commercial solutions BAIDU-UNIT and AI2sql, mark the first experimental case where natural language processing (NLP) models have been used as an attack vector.

    There are many ways to install backdoors in pre-trained language models (PLMs) by poisoning training samples, such as word substitution, development of special prompts, and changing sentence styles. Attacks on 4 different open source models (BART-BASE, BART-LARGE, T5-BASE and T5-3B) using malicious images have achieved 100% success rate with little performance impact, making such issues hard to detect in the real world.

    As a mitigation, experts suggest including classifiers to check for suspicious strings in inputs, evaluate off-the-shelf models to prevent supply chain threats, and adhere to software engineering best practices.

    Author DeepWeb
    Firmware vulnerabilities in Qualcomm Snapdragon allow hackers to control even a turned off computer
    Marijuana microdosing

    Comments 0

    Add comment